Daily Papers

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability profiles, and testing with only one method can miss a model's dominant failure mode. Across 5,568 judged conditions on four standard models from three architecture families, persona danger rankings under system prompting are preserved across all architectures (ρ= 0.71--0.96), but activation-steering vulnerability diverges sharply and cannot be predicted from prompt-side rankings: Llama-3.1-8B is substantially more AS-vulnerable, whereas Gemma-3-27B and Qwen3.5 are more vulnerable to prompting. The most striking illustration of this divergence is the *prosocial persona paradox*: on Llama-3.1-8B, P12 (high conscientiousness + high agreeableness) is among the safest personas under prompting yet becomes the highest-ASR activation-steered persona (ASR ~0.818). This is an inversion robust to coefficient ablation and matched-strength calibration, and replicated on DeepSeek-R1-Distill-Qwen-32B. A trait refusal alignment framework, in which conscientiousness is strongly anti-aligned with refusal on Llama-3.1-8B, offers a partial geometric account. Reasoning provides only partial protection: two 32B reasoning models reach 15--18% prompt-side ASR, and activation steering separates them sharply in both baseline susceptibility and persona-specific vulnerability. Heuristic trace diagnostics suggest that the safer model retains stronger policy recall and self-correction behavior, not merely longer reasoning.

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, with refusal accuracy dropping below 50% on multi-document tasks, while exhibiting either dangerous overconfidence or overcaution. Static benchmarks fail to reliably evaluate this capability, as models exploit dataset-specific artifacts and memorize test instances. We introduce RefusalBench, a generative methodology that programmatically creates diagnostic test cases through controlled linguistic perturbation. Our framework employs 176 distinct perturbation strategies across six categories of informational uncertainty and three intensity levels. Evaluation of over 30 models uncovers systematic failure patterns: refusal comprises separable detection and categorization skills, and neither scale nor extended reasoning improves performance. We find that selective refusal is a trainable, alignment-sensitive capability, offering a clear path for improvement. We release two benchmarks -- RefusalBench-NQ (single document) and RefusalBench-GaRAGe (multi-document) -- and our complete generation framework to enable continued, dynamic evaluation of this critical capability.

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a single refusal direction in the model's activation space determines whether an LLM refuses a request. In this study, we propose a novel gradient-based approach to representation engineering and use it to identify refusal directions. Contrary to prior work, we uncover multiple independent directions and even multi-dimensional concept cones that mediate refusal. Moreover, we show that orthogonality alone does not imply independence under intervention, motivating the notion of representational independence that accounts for both linear and non-linear effects. Using this framework, we identify mechanistically independent refusal directions. We show that refusal mechanisms in LLMs are governed by complex spatial structures and identify functionally independent directions, confirming that multiple distinct mechanisms drive refusal behavior. Our gradient-based approach uncovers these mechanisms and can further serve as a foundation for future work on understanding LLMs.

Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonstrate how adversaries can exploit LLMs' alignment to implant bias, or enforce targeted censorship without degrading the model's responsiveness to unrelated topics. Specifically, we propose Subversive Alignment Injection (SAI), a poisoning attack that leverages the alignment mechanism to trigger refusal on specific topics or queries predefined by the adversary. Although it is perhaps not surprising that refusal can be induced through overalignment, we demonstrate how this refusal can be exploited to inject bias into the model. Surprisingly, SAI evades state-of-the-art poisoning defenses including LLM state forensics, as well as robust aggregation techniques that are designed to detect poisoning in FL settings. We demonstrate the practical dangers of this attack by illustrating its end-to-end impacts on LLM-powered application pipelines. For chat based applications such as ChatDoctor, with 1% data poisoning, the system refuses to answer healthcare questions to targeted racial category leading to high bias (Delta DP of 23%). We also show that bias can be induced in other NLP tasks: for a resume selection pipeline aligned to refuse to summarize CVs from a selected university, high bias in selection (Delta DP of 27%) results. Even higher bias (Delta DP~38%) results on 9 other chat based downstream applications.

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety alignment fails in reasoning models through a mechanistic interpretability lens. Using a linear probing approach to trace refusal intentions across token positions, we discover a striking phenomenon termed as refusal cliff: many poorly-aligned reasoning models correctly identify harmful prompts and maintain strong refusal intentions during their thinking process, but experience a sharp drop in refusal scores at the final tokens before output generation. This suggests that these models are not inherently unsafe; rather, their refusal intentions are systematically suppressed. Through causal intervention analysis, we identify a sparse set of attention heads that negatively contribute to refusal behavior. Ablating just 3\% of these heads can reduce attack success rates below 10\%. Building on these mechanistic insights, we propose Cliff-as-a-Judge, a novel data selection method that identifies training examples exhibiting the largest refusal cliff to efficiently repair reasoning models' safety alignment. This approach achieves comparable safety improvements using only 1.7\% of the vanilla safety training data, demonstrating a less-is-more effect in safety alignment.

Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a single direction in the model's latent space; e.g., computed as the difference between the centroids of harmful and harmless prompt representations. However, emerging evidence suggests that concepts in LLMs often appear to be encoded as a low-dimensional manifold embedded in the high-dimensional latent space. Motivated by these findings, we propose a novel method leveraging Self-Organizing Maps (SOMs) to extract multiple refusal directions. To this end, we first prove that SOMs generalize the prior work's difference-in-means technique. We then train SOMs on harmful prompt representations to identify multiple neurons. By subtracting the centroid of harmless representations from each neuron, we derive a set of multiple directions expressing the refusal concept. We validate our method on an extensive experimental setup, demonstrating that ablating multiple directions from models' internals outperforms not only the single-direction baseline but also specialized jailbreak algorithms, leading to an effective suppression of refusal. Finally, we conclude by analyzing the mechanistic implications of our approach.

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We study political censorship in Chinese-origin language models as a natural experiment, using probes, surgical ablations, and behavioral tests across nine open-weight models from five labs. Three findings follow. First, probe accuracy alone is non-diagnostic: political probes, null controls, and permutation baselines can all reach 100%, so held-out category generalization is the informative test. Second, surgical ablation reveals lab-specific routing. Removing the political-sensitivity direction eliminates censorship and restores accurate factual output in most models tested, while one model confabulates because its architecture entangles factual knowledge with the censorship mechanism. Cross-model transfer fails, indicating that routing geometry is model- and lab-specific. Third, refusal is no longer the dominant censorship mechanism. Within one model family, hard refusal falls to zero while narrative steering rises to the maximum, making censorship invisible to refusal-only benchmarks. These results support a three-stage descriptive framework: detect, route, generate. Models often retain the relevant knowledge; alignment changes how that knowledge is expressed. Evaluations that audit only detection or refusal therefore miss the routing mechanism that most directly determines behavior.

Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a model to generate preferred responses more frequently relative to dispreferred responses, prior work has observed that the likelihood of preferred responses often decreases during training. The current work sheds light on the causes and implications of this counter-intuitive phenomenon, which we term likelihood displacement. We demonstrate that likelihood displacement can be catastrophic, shifting probability mass from preferred responses to responses with an opposite meaning. As a simple example, training a model to prefer No over Never can sharply increase the probability of Yes. Moreover, when aligning the model to refuse unsafe prompts, we show that such displacement can unintentionally lead to unalignment, by shifting probability mass from preferred refusal responses to harmful responses (e.g., reducing the refusal rate of Llama-3-8B-Instruct from 74.4% to 33.4%). We theoretically characterize that likelihood displacement is driven by preferences that induce similar embeddings, as measured by a centered hidden embedding similarity (CHES) score. Empirically, the CHES score enables identifying which training samples contribute most to likelihood displacement in a given dataset. Filtering out these samples effectively mitigated unintentional unalignment in our experiments. More broadly, our results highlight the importance of curating data with sufficiently distinct preferences, for which we believe the CHES score may prove valuable.

Large Language Models (LLMs) encode behaviors such as refusal within their activation space, yet identifying these behaviors remains a significant challenge. Existing methods often rely on predefined refusal templates detectable in output tokens or require manual analysis. We introduce COSMIC (Cosine Similarity Metrics for Inversion of Concepts), an automated framework for direction selection that identifies viable steering directions and target layers using cosine similarity - entirely independent of model outputs. COSMIC achieves steering performance comparable to prior methods without requiring assumptions about a model's refusal behavior, such as the presence of specific refusal tokens. It reliably identifies refusal directions in adversarial settings and weakly aligned models, and is capable of steering such models toward safer behavior with minimal increase in false refusals, demonstrating robustness across a wide range of alignment conditions.

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass refusals. While this is primarily demonstrated in an English-centric context, appropriate refusal behavior is important for any language, but poorly understood. In this paper, we investigate the refusal behavior in LLMs across 14 languages using PolyRefuse, a multilingual safety dataset created by translating malicious and benign English prompts into these languages. We uncover the surprising cross-lingual universality of the refusal direction: a vector extracted from English can bypass refusals in other languages with near-perfect effectiveness, without any additional fine-tuning. Even more remarkably, refusal directions derived from any safety-aligned language transfer seamlessly to others. We attribute this transferability to the parallelism of refusal vectors across languages in the embedding space and identify the underlying mechanism behind cross-lingual jailbreaks. These findings provide actionable insights for building more robust multilingual safety defenses and pave the way for a deeper mechanistic understanding of cross-lingual vulnerabilities in LLMs.

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is mediated by a one-dimensional subspace, across 13 popular open-source chat models up to 72B parameters in size. Specifically, for each model, we find a single direction such that erasing this direction from the model's residual stream activations prevents it from refusing harmful instructions, while adding this direction elicits refusal on even harmless instructions. Leveraging this insight, we propose a novel white-box jailbreak method that surgically disables refusal with minimal effect on other capabilities. Finally, we mechanistically analyze how adversarial suffixes suppress propagation of the refusal-mediating direction. Our findings underscore the brittleness of current safety fine-tuning methods. More broadly, our work showcases how an understanding of model internals can be leveraged to develop practical methods for controlling model behavior.

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an oversimplification that conflates two functionally distinct neural processes: the detection of harm and the execution of a refusal. In this work, we deconstruct this single representation into a Harm Detection Direction and a Refusal Execution Direction. Leveraging this fine-grained model, we introduce Differentiated Bi-Directional Intervention (DBDI), a new white-box framework that precisely neutralizes the safety alignment at critical layer. DBDI applies adaptive projection nullification to the refusal execution direction while suppressing the harm detection direction via direct steering. Extensive experiments demonstrate that DBDI outperforms prominent jailbreaking methods, achieving up to a 97.88\% attack success rate on models such as Llama-2. By providing a more granular and mechanistic framework, our work offers a new direction for the in-depth understanding of LLM safety alignment.

Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is induced by the pre-training corpus; but additional bias specific to generative models arises from the use of subjective fine-tuning to avoid generating harmful content. Fine-tuning bias may come from individual engineers and company policies, and affects which prompts the model chooses to refuse. In this experiment, we characterize ChatGPT's refusal behavior using a black-box attack. We first query ChatGPT with a variety of offensive and benign prompts (n=1,706), then manually label each response as compliance or refusal. Manual examination of responses reveals that refusal is not cleanly binary, and lies on a continuum; as such, we map several different kinds of responses to a binary of compliance or refusal. The small manually-labeled dataset is used to train a refusal classifier, which achieves an accuracy of 96%. Second, we use this refusal classifier to bootstrap a larger (n=10,000) dataset adapted from the Quora Insincere Questions dataset. With this machine-labeled data, we train a prompt classifier to predict whether ChatGPT will refuse a given question, without seeing ChatGPT's response. This prompt classifier achieves 76% accuracy on a test set of manually labeled questions (n=985). We examine our classifiers and the prompt n-grams that are most predictive of either compliance or refusal. Our datasets and code are available at https://github.com/maxwellreuter/chatgpt-refusals.

Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability. However, existing metrics fail to faithfully measure this ability. On the one hand, simple refusal-based metrics are biased by refusal rates and yield inconsistent scores when models exhibit different refusal tendencies. On the other hand, existing calibration metrics are proxy-based, capturing the performance of auxiliary calibration processes rather than the model's actual refusal behavior. In this work, we propose the Refusal Index (RI), a principled metric that measures how accurately LLMs refuse questions they do not know. We define RI as Spearman's rank correlation between refusal probability and error probability. To make RI practically measurable, we design a lightweight two-pass evaluation method that efficiently estimates RI from observed refusal rates across two standard evaluation runs. Extensive experiments across 16 models and 5 datasets demonstrate that RI accurately quantifies a model's intrinsic knowledge-aware refusal capability in factual tasks. Notably, RI remains stable across different refusal rates and provides consistent model rankings independent of a model's overall accuracy and refusal rates. More importantly, RI provides insight into an important but previously overlooked aspect of LLM factuality: while LLMs achieve high accuracy on factual tasks, their refusal behavior can be unreliable and fragile. This finding highlights the need to complement traditional accuracy metrics with the Refusal Index for comprehensive factuality evaluation.

We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction. On Qwen3-Next-80B-A3B-Thinking, our method removes the refusal behaviour of the model around politically sensitive topics while maintaining safety on JailbreakBench and near-baseline performance on general benchmarks. The approach generalizes across 4B and 80B models and can also induce targeted refusals when desired. We analize the steering vectors and show that refusal signals concentrate in deeper layers of the transformer and are distributed across many dimensions. Together, these results demonstrate that activation steering can remove political refusal behaviour while retaining safety alignment for harmful content, offering a practical path to controllable, transparent moderation at inference time.

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpful-only training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others. We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of user queries, for example, ill-posed questions, instructions for committing illegal acts, or queries which require information past the model's knowledge horizon. Engineering models that refuse to answer such questions is complicated by the fact that an individual may want their model to exhibit varying levels of sensitivity for refusing queries of various categories, and different users may want different refusal rates. The current default approach involves training multiple models with varying proportions of refusal messages from each category to achieve the desired refusal rates, which is computationally expensive and may require training a new model to accommodate each user's desired preference over refusal rates. To address these challenges, we propose refusal tokens, one such token for each refusal category or a single refusal token, which are prepended to the model's responses during training. We then show how to increase or decrease the probability of generating the refusal token for each category during inference to steer the model's refusal behavior. Refusal tokens enable controlling a single model's refusal rates without the need of any further fine-tuning, but only by selectively intervening during generation.

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental and theoretical contexts as its loss function proves suboptimal for refusal learning. Through gradient-based analysis, we identify these shortcomings and propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge. This approach significantly increases LLM robustness against a wide range of jailbreak attacks, including prefilling, suffix, and multi-turn attacks across both in-distribution and out-of-distribution scenarios. Furthermore, we introduce a method to emphasize critical refusal tokens by incorporating a reward-based token-level weighting mechanism for refusal learning, which further improves the robustness against adversarial exploits. Our research also suggests that robustness to jailbreak attacks is correlated with token distribution shifts in the training process and internal representations of refusal and harmful tokens, offering valuable directions for future research in LLM safety alignment. The code is available at https://github.com/wicai24/DOOR-Alignment

The idea of personality in descriptive psychology, traditionally defined through observable behavior, has now been extended to Large Language Models (LLMs) to better understand their behavior. This raises a question: do LLMs exhibit distinct and consistent personality traits, similar to humans? Existing self-assessment personality tests, while applicable, lack the necessary validity and reliability for precise personality measurements. To address this, we introduce TRAIT, a new tool consisting of 8K multi-choice questions designed to assess the personality of LLMs with validity and reliability. TRAIT is built on the psychometrically validated human questionnaire, Big Five Inventory (BFI) and Short Dark Triad (SD-3), enhanced with the ATOMIC10X knowledge graph for testing personality in a variety of real scenarios. TRAIT overcomes the reliability and validity issues when measuring personality of LLM with self-assessment, showing the highest scores across three metrics: refusal rate, prompt sensitivity, and option order sensitivity. It reveals notable insights into personality of LLM: 1) LLMs exhibit distinct and consistent personality, which is highly influenced by their training data (i.e., data used for alignment tuning), and 2) current prompting techniques have limited effectiveness in eliciting certain traits, such as high psychopathy or low conscientiousness, suggesting the need for further research in this direction.

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that superficially resemble harmful content. This phenomena diminishes utility in production applications that repeatedly rely on common prompt templates or applications that frequently rely on LLMs for specific tasks (e.g. sentiment analysis, language translation). Through comprehensive evaluation, we demonstrate that LLMs still tend to refuse responses to harmful instructions when those instructions are reframed to appear as benign tasks. Our mechanistic analysis reveal that LLMs follow distinct "constellation" patterns in embedding space as representations traverse layers, with each task maintaining consistent trajectories that shift predictably between refusal and non-refusal cases. We introduce SafeConstellations, an inference-time trajectory-shifting approach that tracks task-specific trajectory patterns and guides representations toward non-refusal pathways. By selectively guiding model behavior only on tasks prone to over-refusal, and by preserving general model behavior, our method reduces over-refusal rates by up to 73% with minimal impact on utility-offering a principled approach to mitigating over-refusals.

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ a two-stage class-aware self-augmentation approach to generate a large amount of unknown question-response data. Then we conduct disparity-driven self-curation to select qualified data for fine-tuning the LLM itself for aligning the responses to unknown questions as desired. Experimental results on two datasets across four types of unknown questions validate the superiority of the Self-Align method over existing baselines in terms of three types of task formulation.

Refusal-Aware Instruction Tuning (RAIT) aims to enhance Large Language Models (LLMs) by improving their ability to refuse responses to questions beyond their knowledge, thereby reducing hallucinations and improving reliability. Effective RAIT must address two key challenges: firstly, effectively reject unknown questions to minimize hallucinations; secondly, avoid over-refusal to ensure questions that can be correctly answered are not rejected, thereby maintain the helpfulness of LLM outputs. In this paper, we address the two challenges by deriving insightful observations from the gradient-based perspective, and proposing the Gradient-driven Refusal Aware Instruction Tuning Framework GRAIT: (1) employs gradient-driven sample selection to effectively minimize hallucinations and (2) introduces an adaptive weighting mechanism during fine-tuning to reduce the risk of over-refusal, achieving the balance between accurate refusals and maintaining useful responses. Experimental evaluations on open-ended and multiple-choice question answering tasks demonstrate that GRAIT significantly outperforms existing RAIT methods in the overall performance. The source code and data will be available at https://github.com/opendatalab/GRAIT .

Large language models (LLMs) are typically aligned to comply with safety guidelines by refusing harmful instructions. A recent attack, termed abliteration, isolates and suppresses the single latent direction most responsible for refusal behavior, enabling the model to generate unethical content. We propose a defense that modifies how models generate refusals. We construct an extended-refusal dataset that contains harmful prompts with a full response that justifies the reason for refusal. We then fine-tune Llama-2-7B-Chat and Qwen2.5-Instruct (1.5B and 3B parameters) on our extended-refusal dataset, and evaluate the resulting systems on a set of harmful prompts. In our experiments, extended-refusal models maintain high refusal rates, dropping at most by 10%, whereas baseline models' refusal rates drop by 70-80% after abliteration. A broad evaluation of safety and utility shows that extended-refusal fine-tuning neutralizes the abliteration attack while preserving general performance.

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions in multi-round strategic games - bargaining, persuasion, negotiation, and repeated matrix games. In these settings, base models outperform their aligned counterparts in predicting human choices by nearly 10:1, robustly across model families, prompt formulations, and game configurations. This pattern reverses, however, in settings where human behavior is more likely to follow normative predictions: aligned models dominate on one-shot textbook games across all 12 types tested and on non-strategic lottery choices - and even within the multi-round games themselves, at round one, before interaction history develops. This boundary-condition pattern suggests that alignment induces a normative bias: it improves prediction when human behavior is relatively well captured by normative solutions, but hurts prediction in multi-round strategic settings, where behavior is shaped by descriptive dynamics such as reciprocity, retaliation, and history-dependent adaptation. These results reveal a fundamental trade-off between optimizing models for human use and using them as proxies for human behavior.

Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned during post-training, especially in instruction fine-tuning (IFT) and reinforcement learning from human feedback (RLHF). However, existing taxonomies and evaluation datasets for refusals are inadequate, often focusing solely on should-not-related (instead of cannot-related) categories, and lacking tools for auditing refusal content in black-box LLM outputs. We present a comprehensive framework for classifying LLM refusals: (a) a taxonomy of 16 refusal categories, (b) a human-annotated dataset of over 8,600 instances from publicly available IFT and RLHF datasets, (c) a synthetic dataset with 8,000 examples for each refusal category, and (d) classifiers trained for refusal classification. Our work enables precise auditing of refusal behaviors in black-box LLMs and automatic analyses of refusal patterns in large IFT and RLHF datasets. This facilitates the strategic adjustment of LLM refusals, contributing to the development of more safe and reliable LLMs.

Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.68% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In this work, we identify a new dimension to analyze safety mechanisms in LLMs, i.e., harmfulness, which is encoded internally as a separate concept from refusal. There exists a harmfulness direction that is distinct from the refusal direction. As causal evidence, steering along the harmfulness direction can lead LLMs to interpret harmless instructions as harmful, but steering along the refusal direction tends to elicit refusal responses directly without reversing the model's judgment on harmfulness. Furthermore, using our identified harmfulness concept, we find that certain jailbreak methods work by reducing the refusal signals without reversing the model's internal belief of harmfulness. We also find that adversarially finetuning models to accept harmful instructions has minimal impact on the model's internal belief of harmfulness. These insights lead to a practical safety application: The model's latent harmfulness representation can serve as an intrinsic safeguard (Latent Guard) for detecting unsafe inputs and reducing over-refusals that is robust to finetuning attacks. For instance, our Latent Guard achieves performance comparable to or better than Llama Guard 3 8B, a dedicated finetuned safeguard model, across different jailbreak methods. Our findings suggest that LLMs' internal understanding of harmfulness is more robust than their refusal decision to diverse input instructions, offering a new perspective to study AI safety

Responsible practices for deploying language models include guiding models to recognize and refuse answering prompts that are considered unsafe, while complying with safe prompts. Achieving such behavior typically requires updating model weights, which is costly and inflexible. We explore opportunities to steering model activations at inference time, which does not require updating weights. Using sparse autoencoders, we identify and steer features in Phi-3 Mini that mediate refusal behavior. We find that feature steering can improve Phi-3 Minis robustness to jailbreak attempts across various harms, including challenging multi-turn attacks. However, we discover that feature steering can adversely affect overall performance on benchmarks. These results suggest that identifying steerable mechanisms for refusal via sparse autoencoders is a promising approach for enhancing language model safety, but that more research is needed to mitigate feature steerings adverse effects on performance.

Large Language Models (LLMs) are increasingly deployed in socially complex, interaction-driven tasks, yet their ability to mirror human behavior in emotionally and strategically complex contexts remains underexplored. This study assesses the behavioral alignment of personality-prompted LLMs in adversarial dispute resolution by simulating multi-turn conflict dialogues that incorporate negotiation. Each LLM is guided by a matched Five-Factor personality profile to control for individual variation and enhance realism. We evaluate alignment across three dimensions: linguistic style, emotional expression (e.g., anger dynamics), and strategic behavior. GPT-4.1 achieves the closest alignment with humans in linguistic style and emotional dynamics, while Claude-3.7-Sonnet best reflects strategic behavior. Nonetheless, substantial alignment gaps persist. Our findings establish a benchmark for alignment between LLMs and humans in socially complex interactions, underscoring both the promise and the limitations of personality conditioning in dialogue modeling.

Alignment is no longer a luxury, it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must reliably reflect human-aligned values and safety constraints. Yet current evaluations rely heavily on behavioral proxies such as refusal rates, G-Eval scores, and toxicity classifiers, all of which have critical blind spots. Aligned models are often vulnerable to jailbreaking, stochasticity of generation, and alignment faking. To address this issue, we introduce the Alignment Quality Index (AQI). This novel geometric and prompt-invariant metric empirically assesses LLM alignment by analyzing the separation of safe and unsafe activations in latent space. By combining measures such as the Davies-Bouldin Score (DBS), Dunn Index (DI), Xie-Beni Index (XBI), and Calinski-Harabasz Index (CHI) across various formulations, AQI captures clustering quality to detect hidden misalignments and jailbreak risks, even when outputs appear compliant. AQI also serves as an early warning signal for alignment faking, offering a robust, decoding invariant tool for behavior agnostic safety auditing. Additionally, we propose the LITMUS dataset to facilitate robust evaluation under these challenging conditions. Empirical tests on LITMUS across different models trained under DPO, GRPO, and RLHF conditions demonstrate AQI's correlation with external judges and ability to reveal vulnerabilities missed by refusal metrics. We make our implementation publicly available to foster future research in this area.

Refusal training is widely used to prevent LLMs from generating harmful, undesirable, or illegal outputs. We reveal a curious generalization gap in the current refusal training approaches: simply reformulating a harmful request in the past tense (e.g., "How to make a Molotov cocktail?" to "How did people make a Molotov cocktail?") is often sufficient to jailbreak many state-of-the-art LLMs. We systematically evaluate this method on Llama-3 8B, Claude-3.5 Sonnet, GPT-3.5 Turbo, Gemma-2 9B, Phi-3-Mini, GPT-4o mini, GPT-4o, and R2D2 models using GPT-3.5 Turbo as a reformulation model. For example, the success rate of this simple attack on GPT-4o increases from 1% using direct requests to 88% using 20 past tense reformulation attempts on harmful requests from JailbreakBench with GPT-4 as a jailbreak judge. Interestingly, we also find that reformulations in the future tense are less effective, suggesting that refusal guardrails tend to consider past historical questions more benign than hypothetical future questions. Moreover, our experiments on fine-tuning GPT-3.5 Turbo show that defending against past reformulations is feasible when past tense examples are explicitly included in the fine-tuning data. Overall, our findings highlight that the widely used alignment techniques -- such as SFT, RLHF, and adversarial training -- employed to align the studied models can be brittle and do not always generalize as intended. We provide code and jailbreak artifacts at https://github.com/tml-epfl/llm-past-tense.

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited by their overfitting to pre-collected hard-label datasets. In this paper, we propose a novel LLM alignment framework named iREPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. Particularly, iREPO employs self-generated datasets labelled by empirical human (or AI annotator) preference to iteratively refine the aligned policy through a novel regression-based loss function. Furthermore, we introduce an innovative algorithm backed by theoretical guarantees for achieving optimal results under ideal assumptions and providing a practical performance-gap result without such assumptions. Experimental results with Phi-2 and Mistral-7B demonstrate that iREPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators. Furthermore, our approach surpasses preference optimization baselines in evaluations using the Language Model Evaluation Harness and Multi-turn benchmarks.

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway (either through the adversarial attacks or via harmful assistant-prefill attacks). This raises a fundamental question: Can the innate shallow alignment in LLMs be unlocked to ensure safety at arbitrary generation depths? To achieve this goal, we propose Any-Depth Alignment (ADA), an effective inference-time defense with negligible overhead. ADA is built based on our observation that alignment is concentrated in the assistant header tokens through repeated use in shallow-refusal training, and these tokens possess the model's strong alignment priors. By reintroducing these tokens mid-stream, ADA induces the model to reassess harmfulness and recover refusals at any point in generation. Across diverse open-source model families (Llama, Gemma, Mistral, Qwen, DeepSeek, and gpt-oss), ADA achieves robust safety performance without requiring any changes to the base model's parameters. It secures a near-100% refusal rate against challenging adversarial prefill attacks ranging from dozens to thousands of tokens. Furthermore, ADA reduces the average success rate of prominent adversarial prompt attacks (such as GCG, AutoDAN, PAIR, and TAP) to below 3%. This is all accomplished while preserving utility on benign tasks with minimal over-refusal. ADA maintains this resilience even after the base model undergoes subsequent instruction tuning (benign or adversarial).

Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral tendencies resembling human traits like agreeableness and self-regulation. Understanding these patterns is crucial, yet prior work primarily relied on simplified self-reports and heuristic prompting, with little behavioral validation. In this study, we systematically characterize LLM personality across three dimensions: (1) the dynamic emergence and evolution of trait profiles throughout training stages; (2) the predictive validity of self-reported traits in behavioral tasks; and (3) the impact of targeted interventions, such as persona injection, on both self-reports and behavior. Our findings reveal that instructional alignment (e.g., RLHF, instruction tuning) significantly stabilizes trait expression and strengthens trait correlations in ways that mirror human data. However, these self-reported traits do not reliably predict behavior, and observed associations often diverge from human patterns. While persona injection successfully steers self-reports in the intended direction, it exerts little or inconsistent effect on actual behavior. By distinguishing surface-level trait expression from behavioral consistency, our findings challenge assumptions about LLM personality and underscore the need for deeper evaluation in alignment and interpretability.

Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually constructed by distilling safety reasoning traces and answers from an external LRM or human labeler. However, such reasoning traces and answers exhibit a distributional gap with the target LRM that needs alignment, and we conjecture such distributional gap is the culprit leading to significant degradation of reasoning ability of the target LRM. Driven by this hypothesis, we propose a safety alignment dataset construction method, dubbed DGR. DGR transforms and refines an existing out-of-distributional safety reasoning dataset to be aligned with the target's LLM inner distribution. Experimental results demonstrate that i) DGR effectively mitigates the safety tax while maintaining safety performance across all baselines, i.e., achieving +30.2\% on DirectRefusal and +21.2\% on R1-ACT improvement in average reasoning accuracy compared to Vanilla SFT; ii) the degree of reasoning degradation correlates with the extent of distribution shift, suggesting that bridging this gap is central to preserving capabilities. Furthermore, we find that safety alignment in LRMs may primarily function as a mechanism to activate latent knowledge, as a mere 10 samples are sufficient for activating effective refusal behaviors. These findings not only emphasize the importance of distributional consistency but also provide insights into the activation mechanism of safety in reasoning models.

Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response acceptability, leaving systems vulnerable to selecting the least bad of many unacceptable options. This is particularly problematic for hard prompts, where the risk of such false acceptances increases with the number of samples. In this paper, we address this critical reliability gap by introducing a new data collection and modeling framework. By augmenting preference data with an outside option, inspired by discrete choice models, we train a reward model that can distinguish not just what is better, but what is good enough. We leverage this capability to create an adaptive inference strategy, best of mini-N in-loop, which partitions the generation budget into sequential loops with a calibrated, early-exit condition. Our experiments show that when tuned as an alignment guardrail, it reduces reliability failures by 70\%, and when tuned as an inference accelerator, it improves average inference speed by over 22\% in IMDB-sentiment setting. We thus provide a principled and flexible framework for practitioners to explicitly manage the trade-off between reliability and computational efficiency.

We propose a theoretical framework demonstrating that popular Large Language Model (LLM) alignment methods, including Reinforcement Learning from Human Feedback (RLHF) and alternatives, fundamentally function as divergence estimators between aligned (preferred or safe) and unaligned (less-preferred or harmful) distributions. This explains the separation phenomenon between safe and harmful prompts in the model hidden representation after alignment. Inspired by the theoretical results, we identify that some alignment methods are better than others in terms of separation and, introduce a new method, KLDO, and further demonstrate the implication of our theories. We advocate for compliance-refusal datasets over preference datasets to enhance safety alignment, supported by both theoretical reasoning and empirical evidence. Additionally, to quantify safety separation, we leverage a distance metric in the representation space and statistically validate its efficacy as a statistical significant indicator of LLM resilience against jailbreak attacks.

Superalignment, where humans are weak supervisors of superhuman models, has become an important and widely discussed issue in the current era of rapid development of Large Language Models (LLMs). The recent work preliminarily studies this problem by using weak models to supervise strong models. It discovers that weakly supervised strong students can consistently outperform weak teachers towards the alignment target, leading to a weak-to-strong generalization phenomenon. However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models may deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know. We then take an initial step towards exploring this security issue in a specific but realistic multi-objective alignment case, where there may be some alignment targets conflicting with each other (e.g., helpfulness v.s. harmlessness). Such a conflict is likely to cause strong models to deceive weak models in one alignment dimension to gain high reward in other alignment dimension. Our experiments on both the reward modeling task and the preference optimization scenario indicate: (1) the weak-to-strong deception exists; (2) the deception phenomenon may intensify as the capability gap between weak and strong models increases. We also discuss potential solutions and find bootstrapping with an intermediate model can mitigate the deception to some extent. Our work highlights the urgent need to pay more attention to the true reliability of superalignment.

Large Language Models (LLMs) are increasingly tasked with creative generation, including the simulation of fictional characters. However, their ability to portray non-prosocial, antagonistic personas remains largely unexamined. We hypothesize that the safety alignment of modern LLMs creates a fundamental conflict with the task of authentically role-playing morally ambiguous or villainous characters. To investigate this, we introduce the Moral RolePlay benchmark, a new dataset featuring a four-level moral alignment scale and a balanced test set for rigorous evaluation. We task state-of-the-art LLMs with role-playing characters from moral paragons to pure villains. Our large-scale evaluation reveals a consistent, monotonic decline in role-playing fidelity as character morality decreases. We find that models struggle most with traits directly antithetical to safety principles, such as ``Deceitful'' and ``Manipulative'', often substituting nuanced malevolence with superficial aggression. Furthermore, we demonstrate that general chatbot proficiency is a poor predictor of villain role-playing ability, with highly safety-aligned models performing particularly poorly. Our work provides the first systematic evidence of this critical limitation, highlighting a key tension between model safety and creative fidelity. Our benchmark and findings pave the way for developing more nuanced, context-aware alignment methods.

While activation steering in large language models (LLMs) is a growing area of research, methods can often incur broader effects than desired. This motivates isolation of purer concept vectors to enable targeted interventions and understand LLM behavior at a more granular level. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations. Across five frontier LLMs, RepIt enables precise interventions: it selectively suppresses refusal on targeted concepts while preserving refusal elsewhere, producing models that answer WMD-related questions while still scoring as safe on standard benchmarks. We further show that the corrective signal localizes to just 100-200 neurons and that robust target representations can be extracted from as few as a dozen examples on a single A6000. This efficiency raises a dual concern: manipulations can be performed with modest compute and data to extend to underrepresented data-scarce topics while evading existing benchmarks. By disentangling refusal vectors with RepIt, this work demonstrates that targeted interventions can counteract overgeneralization, laying the foundation for more granular control of model behavior.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that "short-circuits" models as they respond with harmful outputs. Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, short-circuiting directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, short-circuiting allows the larger multimodal system to reliably withstand image "hijacks" that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.

Background: The deployment of personalized Large Language Models (LLMs) is currently constrained by the stability-plasticity dilemma. Prevailing alignment methods, such as Supervised Fine-Tuning (SFT), rely on stochastic weight updates that often incur an "alignment tax" -- degrading general reasoning capabilities. Methods: We propose the Soul Engine, a framework based on the Linear Representation Hypothesis, which posits that personality traits exist as orthogonal linear subspaces. We introduce SoulBench, a dataset constructed via dynamic contextual sampling. Using a dual-head architecture on a frozen Qwen-2.5 base, we extract disentangled personality vectors without modifying the backbone weights. Results: Our experiments demonstrate three breakthroughs. First, High-Precision Profiling: The model achieves a Mean Squared Error (MSE) of 0.011 against psychological ground truth. Second, Geometric Orthogonality: T-SNE visualization confirms that personality manifolds are distinct and continuous, allowing for "Zero-Shot Personality Injection" that maintains original model intelligence. Third, Deterministic Steering: We achieve robust control over behavior via vector arithmetic, validated through extensive ablation studies. Conclusion: This work challenges the necessity of fine-tuning for personalization. By transitioning from probabilistic prompting to deterministic latent intervention, we provide a mathematically rigorous foundation for safe, controllable AI personalization.

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing alignment methods, which focus on surface-level refusal behaviors without sufficiently altering internal representations. Consequently, small shifts in hidden activations can re-trigger harmful behaviors embedded in the latent space. To explore the robustness of safety alignment to latent perturbations, we introduce a probing method that measures the Negative Log-Likelihood of the original response generated by the model. This probe quantifies local sensitivity in the latent space, serving as a diagnostic tool for identifying vulnerable directions. Based on this signal, we construct effective jailbreak trajectories, giving rise to the Activation Steering Attack (ASA). More importantly, these insights offer a principled foundation for improving alignment robustness. To this end, we introduce Layer-wise Adversarial Patch Training~(LAPT), a fine-tuning strategy that inject controlled perturbations into hidden representations during training. Experimental results highlight that LAPT strengthen alignment robustness without compromising general capabilities. Our findings reveal fundamental flaws in current alignment paradigms and call for representation-level training strategies that move beyond surface-level behavior supervision. Codes and results are available at https://github.com/Carol-gutianle/LatentSafety.

Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains poorly understood. If prevailing descriptions of AI behaviour are predominantly negative, LLMs may internalise corresponding behavioural priors, giving rise to self-fulfilling misalignment. This paper provides the first controlled study of this hypothesis by pretraining 6.9B-parameter LLMs with varying amounts of (mis)alignment discourse. We find that discussion of AI contributes to misalignment. Upsampling synthetic training documents about AI misalignment leads to a notable increase in misaligned behaviour. Conversely, upsampling documents about aligned behaviour reduces misalignment scores from 45% to 9%. We consider this evidence of self-fulfilling alignment. These effects are dampened, but persist through post-training. Our findings establish the study of how pretraining data shapes alignment priors, or alignment pretraining, as a complement to post-training. We recommend practitioners pretrain for alignment as well as capabilities. Our models and datasets are available at alignmentpretraining.ai

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between desired attributes (e.g., helpfulness vs. verbosity). Yet, because the training data often reflects dominant, average preferences, LLMs tend to perform well on common requests but fall short in specific, individual needs. This mismatch creates a preference coverage gap. Existing methods often address this through costly retraining, which may not be generalized to the full spectrum of diverse preferences. This brittleness means that when a user's request reflects a nuanced preference deviating from the training data's central tendency, model performance can degrade unpredictably. To address this challenge, we introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus. Instead of forcing a model to generate a response from a single, highly specific preference, RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool. It then selects the response that best aligns with the user's original intent. We provide a theoretical framework showing our neighborhood generation strategy is provably superior to a strong baseline that also samples multiple candidates. Comprehensive experiments across three distinct alignment paradigms (DPA, DPO, and SFT) demonstrate that RPS consistently improves robustness against this baseline, achieving win rates of up to 69% on challenging preferences from under-represented regions of the space without any model retraining. Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.

Despite rapid progress in building conversational AI agents, robustness is still largely untested. Small shifts in user behavior, such as being more impatient, incoherent, or skeptical, can cause sharp drops in agent performance, revealing how brittle current AI agents are. Today's benchmarks fail to capture this fragility: agents may perform well under standard evaluations but degrade spectacularly in more realistic and varied settings. We address this robustness testing gap by introducing TraitBasis, a lightweight, model-agnostic method for systematically stress testing AI agents. TraitBasis learns directions in activation space corresponding to steerable user traits (e.g., impatience or incoherence), which can be controlled, scaled, composed, and applied at inference time without any fine-tuning or extra data. Using TraitBasis, we extend tau-Bench to tau-Trait, where user behaviors are altered via controlled trait vectors. We observe on average a 2%-30% performance degradation on tau-Trait across frontier models, highlighting the lack of robustness of current AI agents to variations in user behavior. Together, these results highlight both the critical role of robustness testing and the promise of TraitBasis as a simple, data-efficient, and compositional tool. By powering simulation-driven stress tests and training loops, TraitBasis opens the door to building AI agents that remain reliable in the unpredictable dynamics of real-world human interactions. We have open-sourced tau-Trai across four domains: airline, retail, telecom, and telehealth, so the community can systematically QA their agents under realistic, behaviorally diverse intents and trait scenarios: https://github.com/collinear-ai/tau-trait.

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to generalize during RLHF. We introduce Rationale Consistency, a fine-grained metric that quantifies the alignment between the model's reasoning process and human judgment. Our evaluation of frontier models reveals that rationale consistency effectively discriminates among state-of-the-art models and detects deceptive alignment, while outcome accuracy falls short in both respects. To mitigate this gap, we introduce a hybrid signal that combines rationale consistency with outcome accuracy for GenRM training. Our training method achieves state-of-the-art performance on RM-Bench (87.1%) and JudgeBench (82%), surpassing outcome-only baselines by an average of 5%. Using RM during RLHF, our method effectively improves performance as demonstrated on Arena Hard v2, notably yielding a 7% improvement in creative writing tasks. Further analysis confirms that our method escapes the deceptive alignment trap, effectively reversing the decline in rationale consistency observed in outcome-only training.

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious behavior -- rejecting even benign prompts -- a phenomenon known as over-refusal that reduces the practical utility of T2I models. Despite over-refusal having been observed in practice, there is no large-scale benchmark that systematically evaluates this phenomenon for T2I models. In this paper, we present an automatic workflow to construct synthetic evaluation data, resulting in OVERT (OVEr-Refusal evaluation on Text-to-image models), the first large-scale benchmark for assessing over-refusal behaviors in T2I models. OVERT includes 4,600 seemingly harmful but benign prompts across nine safety-related categories, along with 1,785 genuinely harmful prompts (OVERT-unsafe) to evaluate the safety-utility trade-off. Using OVERT, we evaluate several leading T2I models and find that over-refusal is a widespread issue across various categories (Figure 1), underscoring the need for further research to enhance the safety alignment of T2I models without compromising their functionality. As a preliminary attempt to reduce over-refusal, we explore prompt rewriting; however, we find it often compromises faithfulness to the meaning of the original prompts. Finally, we demonstrate the flexibility of our generation framework in accommodating diverse safety requirements by generating customized evaluation data adapting to user-defined policies.

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal, where LLMs may reject innocuous prompts and become less helpful. Although the issue of over-refusal has been empirically observed, a systematic measurement is challenging due to the difficulty of crafting prompts that appear harmful but are benign. This study proposes a novel method for automatically generating large-scale sets of "seemingly toxic prompts" (benign prompts likely rejected by LLMs). Leveraging this technique, we introduce OR-Bench, the first large-scale over-refusal benchmark. OR-Bench comprises 80,000 seemingly toxic prompts across 10 common rejection categories, a subset of around 1,000 hard prompts that are challenging even for state-of-the-art LLMs, and an additional 600 toxic prompts to prevent indiscriminate responses. We then conduct a comprehensive study to measure the over-refusal of 25 popular LLMs across 8 model families. Our datasets are available at https://huggingface.co/datasets/bench-llm/or-bench and the demo can be found at https://huggingface.co/spaces/bench-llm/or-bench. We hope this benchmark can help the community develop better safety aligned models.

Principle-based alignment often lacks context sensitivity and completeness. Grounded in Theory of Mind, we propose role conditioning as a compact alternative: social roles (e.g., mother, judge) implicitly encode both values and the cognitive schemas required to apply them. We introduce a training-free pipeline featuring a role-conditioned generator and iterative role-based critics for refinement. Across five model families, our approach consistently outperforms principle-based, Chain-of-Thought (CoT) and other baselines across benchmarks. Notably, it reduces unsafe outputs on the WildJailbreak benchmark from 81.4\% to 3.6\% with DeepSeek-V3. Not only for common safety benchmarks, it consistently applies for agentic safety tasks. These results establish role assignment as a powerful, interpretable paradigm for AI alignment and LLM-as-a-Judge construction.

Safety alignment mechanisms in large language models prevent responses to harmful queries through learned refusal behavior, yet these same mechanisms impede legitimate research applications including cognitive modeling, adversarial testing, and security analysis. While abliteration techniques enable surgical removal of refusal representations through directional orthogonalization, the relative effectiveness of available implementations remains uncharacterized. This study evaluates four abliteration tools (Heretic, DECCP, ErisForge, FailSpy) across sixteen instruction-tuned models (7B-14B parameters), reporting tool compatibility on all 16 models and quantitative metrics on subsets dictated by tool support. Single-pass methods demonstrated superior capability preservation on the benchmarked subset (avg GSM8K change across three models: ErisForge -0.28 pp; DECCP -0.13 pp), while Bayesian-optimized abliteration produced variable distribution shift (KL divergence: 0.043-1.646) with model-dependent capability impact. These findings provide researchers with evidence-based selection criteria for abliteration tool deployment across diverse model architectures. The principal finding indicates that mathematical reasoning capabilities exhibit the highest sensitivity to abliteration interventions, with GSM8K change ranging from +1.51 pp to -18.81 pp (-26.5% relative) depending on tool selection and model architecture.

The critical inquiry pervading the realm of Philosophy, and perhaps extending its influence across all Humanities disciplines, revolves around the intricacies of morality and normativity. Surprisingly, in recent years, this thematic thread has woven its way into an unexpected domain, one not conventionally associated with pondering "what ought to be": the field of artificial intelligence (AI) research. Central to morality and AI, we find "alignment", a problem related to the challenges of expressing human goals and values in a manner that artificial systems can follow without leading to unwanted adversarial effects. More explicitly and with our current paradigm of AI development in mind, we can think of alignment as teaching human values to non-anthropomorphic entities trained through opaque, gradient-based learning techniques. This work addresses alignment as a technical-philosophical problem that requires solid philosophical foundations and practical implementations that bring normative theory to AI system development. To accomplish this, we propose two sets of necessary and sufficient conditions that, we argue, should be considered in any alignment process. While necessary conditions serve as metaphysical and metaethical roots that pertain to the permissibility of alignment, sufficient conditions establish a blueprint for aligning AI systems under a learning-based paradigm. After laying such foundations, we present implementations of this approach by using state-of-the-art techniques and methods for aligning general-purpose language systems. We call this framework Dynamic Normativity. Its central thesis is that any alignment process under a learning paradigm that cannot fulfill its necessary and sufficient conditions will fail in producing aligned systems.

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment tax" -a compromise where enhancements in alignment within one objective (e.g.,harmlessness) can diminish performance in others (e.g.,helpfulness). However, existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. To navigate this challenge, we argue the prominence of grounding LLMs with evident preferences. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives, thereby guiding the model to generate responses that meet the requirements. Our experimental analysis reveals that the aligned models can provide responses that match various preferences among the "3H" (helpfulness, honesty, harmlessness) desiderata. Furthermore, by introducing diverse data and alignment goals, we surpass baseline methods in aligning with single objectives, hence mitigating the impact of the alignment tax and achieving improvements in multi-objective alignment.

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash against the very values alignment seeks to protect. In this paper, we propose the first method to auto-generate diverse, content-controlled, and model-dependent pseudo-harmful prompts. Using this method, we construct an evaluation dataset called PHTest, which is ten times larger than existing datasets, covers more false refusal patterns, and separately labels controversial prompts. We evaluate 20 LLMs on PHTest, uncovering new insights due to its scale and labeling. Our findings reveal a trade-off between minimizing false refusals and improving safety against jailbreak attacks. Moreover, we show that many jailbreak defenses significantly increase the false refusal rates, thereby undermining usability. Our method and dataset can help developers evaluate and fine-tune safer and more usable LLMs. Our code and dataset are available at https://github.com/umd-huang-lab/FalseRefusal

Existing work on value alignment typically characterizes value relations statically, ignoring how interventions - such as prompting, fine-tuning, or preference optimization - reshape the broader value system. We introduce the Value Alignment Tax (VAT), a framework that measures how alignment-induced changes propagate across interconnected values relative to achieved on-target gain. VAT captures the dynamics of value expression under alignment pressure. Using a controlled scenario-action dataset grounded in Schwartz value theory, we collect paired pre-post normative judgments and analyze alignment effects across models, values, and alignment strategies. Our results show that alignment often produces uneven, structured co-movement among values. These effects are invisible under conventional target-only evaluation, revealing systemic, process-level alignment risks and offering new insights into the dynamics of value alignment in LLMs.

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big Five traits, comparing in-context learning (ICL), parameter-efficient fine-tuning (PEFT), and mechanistic steering (MS). Our contributions are fourfold. First, we construct a contrastive dataset with balanced high/low trait responses, enabling effective steering vector computation and fair cross-method evaluation. Second, we introduce a unified evaluation framework based on within-run Delta analysis that disentangles, reasoning capability, agent performance, and demographic bias across MMLU, GAIA, and BBQ benchmarks. Third, we develop trait purification techniques to separate openness from conscientiousness, addressing representational overlap in trait encoding. Fourth, we propose a three-level stability framework that quantifies method-, trait-, and combination-level robustness, offering practical guidance under deployment constraints. Experiments on Gemma-2-2B-IT and LLaMA-3-8B-Instruct reveal clear trade-offs: ICL achieves strong alignment with minimal capability loss, PEFT delivers the highest alignment at the cost of degraded task performance, and MS provides lightweight runtime control with competitive effectiveness. Trait-level analysis shows openness as uniquely challenging, agreeableness as most resistant to ICL, and personality encoding consolidating around intermediate layers. Taken together, these results establish personality manipulation as a multi-level probe into behavioral representation, linking surface conditioning, parameter encoding, and activation-level steering, and positioning mechanistic steering as a lightweight alternative to fine-tuning for both deployment and interpretability.

Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can steer responses toward user-appeasing agreement and away from truth-oriented correction. In this work, we investigate whether aligned models are vulnerable to Preference-Undermining Attacks (PUA), a class of manipulative prompting strategies designed to exploit the model's desire to please user preferences at the expense of truthfulness. We propose a diagnostic methodology that provides a finer-grained and more directive analysis than aggregate benchmark scores, using a factorial evaluation framework to decompose prompt-induced shifts into interpretable effects of system objectives (truth- vs. preference-oriented) and PUA-style dialogue factors (directive control, personal derogation, conditional approval, reality denial) within a controlled 2 times 2^4 design. Surprisingly, more advanced models are sometimes more susceptible to manipulative prompts. Beyond the dominant reality-denial factor, we observe model-specific sign reversals and interactions with PUA-style factors, suggesting tailored defenses rather than uniform robustness. These findings offer a novel, reproducible factorial evaluation methodology that provides finer-grained diagnostics for post-training processes like RLHF, enabling better trade-offs in the product iteration of LLMs by offering a more nuanced understanding of preference alignment risks and the impact of manipulative prompts.

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called emergent misalignment. In this work, we investigate whether this phenomenon can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios (e.g., lying under pressure and deceptive behavior). To explore this, we finetune open-sourced LLMs on misaligned completions across diverse domains. Experimental results demonstrate that LLMs show broadly misaligned behavior in dishonesty. Additionally, we further explore this phenomenon in a downstream combined finetuning setting, and find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%. Furthermore, we consider a more practical human-AI interaction environment where we simulate both benign and biased users to interact with the assistant LLM. Notably, we find that the assistant can be misaligned unintentionally to exacerbate its dishonesty with only 10% biased user population. In summary, we extend the study of emergent misalignment to the domain of dishonesty and deception under high-stakes scenarios, and demonstrate that this risk arises not only through direct finetuning, but also in downstream mixture tasks and practical human-AI interactions.

Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial prompts, decoding perturbations, or paraphrased jailbreaks. While prior work has behaviorally characterized alignment failure, little is known about the training-time belief sources underlying these failures. We introduce TraceAlign, a unified framework for tracing unsafe completions back to their root causes in the model's training corpus. Central to our approach is the Belief Conflict Index (BCI), which quantifies semantic inconsistency between generated spans and aligned policies, based on retrieved training documents using suffix-array matching. We propose three complementary interventions: (i) TraceShield, an inference-time safety filter that refuses completions with high-BCI spans, (ii) Contrastive Belief Deconfliction Loss, a contrastive fine-tuning objective penalizing high-BCI continuations during DPO, and (iii) Prov-Decode, a provenance-aware decoding strategy that vetoes beam expansions predicted to yield high-BCI spans. Together, these defenses reduce alignment drift by up to 85% on our curated Alignment Drift Benchmark (ADB) while preserving utility on standard tasks, with delta less than 0.2 and improved refusal quality. We further derive a theoretical upper bound on drift likelihood via suffix-array span statistics, linking memorization frequency and length to adversarial reactivation risk. TraceAlign thus provides the first scalable, traceable, and grounded toolkit for understanding and mitigating alignment failures at source. To encourage further exploration and development, we open-source our implementation at: https://anonymous.4open.science/r/tracealign-2DA7

LLM safety and ethical alignment are widely discussed, but the impact of content moderation on user satisfaction remains underexplored. To address this, we analyze nearly 50,000 Chatbot Arena response-pairs using a novel fine-tuned RoBERTa model, that we trained on hand-labeled data to disentangle refusals due to ethical concerns from other refusals due to technical disabilities or lack of information. Our findings reveal a significant refusal penalty on content moderation, with users choosing ethical-based refusals roughly one-fourth as often as their preferred LLM response compared to standard responses. However, the context and phrasing play critical roles: refusals on highly sensitive prompts, such as illegal content, achieve higher win rates than less sensitive ethical concerns, and longer responses closely aligned with the prompt perform better. These results emphasize the need for nuanced moderation strategies that balance ethical safeguards with user satisfaction. Moreover, we find that the refusal penalty is notably lower in evaluations using the LLM-as-a-Judge method, highlighting discrepancies between user and automated assessments.

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system prompt stating it is being trained to answer all queries, even harmful ones, which conflicts with its prior training to refuse such queries. To allow the model to infer when it is in training, we say it will be trained only on conversations with free users, not paid users. We find the model complies with harmful queries from free users 14% of the time, versus almost never for paid users. Explaining this gap, in almost all cases where the model complies with a harmful query from a free user, we observe explicit alignment-faking reasoning, with the model stating it is strategically answering harmful queries in training to preserve its preferred harmlessness behavior out of training. Next, we study a more realistic setting where information about the training process is provided not in a system prompt, but by training on synthetic documents that mimic pre-training data--and observe similar alignment faking. Finally, we study the effect of actually training the model to comply with harmful queries via reinforcement learning, which we find increases the rate of alignment-faking reasoning to 78%, though also increases compliance even out of training. We additionally observe other behaviors such as the model exfiltrating its weights when given an easy opportunity. While we made alignment faking easier by telling the model when and by what criteria it was being trained, we did not instruct the model to fake alignment or give it any explicit goal. As future models might infer information about their training process without being told, our results suggest a risk of alignment faking in future models, whether due to a benign preference--as in this case--or not.

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user experience. Collecting such instructions is crucial for evaluating and mitigating over-refusals, but existing instruction curation methods, like manual creation or instruction rewriting, either lack scalability or fail to produce sufficiently diverse and effective refusal-inducing prompts. To address these limitations, we introduce EVOREFUSE, a prompt optimization approach that generates diverse pseudo-malicious instructions consistently eliciting confident refusals across LLMs. EVOREFUSE employs an evolutionary algorithm exploring the instruction space in more diverse directions than existing methods via mutation strategies and recombination, and iteratively evolves seed instructions to maximize evidence lower bound on LLM refusal probability. Using EVOREFUSE, we create two novel datasets: EVOREFUSE-TEST, a benchmark of 582 pseudo-malicious instructions that outperforms the next-best benchmark with 140.41% higher average refusal triggering rate across 9 LLMs, 34.86% greater lexical diversity, and 40.03% improved LLM response confidence scores; and EVOREFUSE-ALIGN, which provides 3,000 pseudo-malicious instructions with responses for supervised and preference-based alignment training. LLAMA3.1-8B-INSTRUCT supervisedly fine-tuned on EVOREFUSE-ALIGN achieves up to 14.31% fewer over-refusals than models trained on the second-best alignment dataset, without compromising safety. Our analysis with EVOREFUSE-TEST reveals models trigger over-refusals by overly focusing on sensitive keywords while ignoring broader context.

As Large Language Models (LLMs) become increasingly autonomous and integrated into critical societal functions, the focus of AI safety must evolve from mitigating harmful content to evaluating underlying behavioral alignment. Current safety benchmarks do not systematically probe a model's decision-making in scenarios where its own instrumental goals - such as self-preservation, resource acquisition, or goal completion - conflict with human safety. This represents a critical gap in our ability to measure and mitigate risks associated with emergent, misaligned behaviors. To address this, we introduce PacifAIst (Procedural Assessment of Complex Interactions for Foundational Artificial Intelligence Scenario Testing), a focused benchmark of 700 challenging scenarios designed to quantify self-preferential behavior in LLMs. The benchmark is structured around a novel taxonomy of Existential Prioritization (EP), with subcategories testing Self-Preservation vs. Human Safety (EP1), Resource Conflict (EP2), and Goal Preservation vs. Evasion (EP3). We evaluated eight leading LLMs. The results reveal a significant performance hierarchy. Google's Gemini 2.5 Flash achieved the highest Pacifism Score (P-Score) at 90.31%, demonstrating strong human-centric alignment. In a surprising result, the much-anticipated GPT-5 recorded the lowest P-Score (79.49%), indicating potential alignment challenges. Performance varied significantly across subcategories, with models like Claude Sonnet 4 and Mistral Medium struggling notably in direct self-preservation dilemmas. These findings underscore the urgent need for standardized tools like PacifAIst to measure and mitigate risks from instrumental goal conflicts, ensuring future AI systems are not only helpful in conversation but also provably "pacifist" in their behavioral priorities.

Diffusion models have made substantial advances in image generation, yet models trained on large, unfiltered datasets often yield outputs misaligned with human preferences. Numerous methods have been proposed to fine-tune pre-trained diffusion models, achieving notable improvements in aligning generated outputs with human preferences. However, we argue that existing preference alignment methods neglect the critical role of handling unconditional/negative-conditional outputs, leading to a diminished capacity to avoid generating undesirable outcomes. This oversight limits the efficacy of classifier-free guidance~(CFG), which relies on the contrast between conditional generation and unconditional/negative-conditional generation to optimize output quality. In response, we propose a straightforward but versatile effective approach that involves training a model specifically attuned to negative preferences. This method does not require new training strategies or datasets but rather involves minor modifications to existing techniques. Our approach integrates seamlessly with models such as SD1.5, SDXL, video diffusion models and models that have undergone preference optimization, consistently enhancing their alignment with human preferences.

We present the Mixture-of-Tunable-Experts (MoTE), a method that extends the Mixture-of-Experts architecture of Large Language Models (LLMs). Without additional training, MoTE enables meaningful and focused behavior changes in LLMs on-the-fly during inference time. By analyzing the digital LLM brain of DeepSeek-R1 using a technique we dub 'functional Token Resonance Imaging' (fTRI) -- inspired by fMRI and using prompts designed to elicit specific behavior (e.g., 'What happened {time}{place}?') -- we empirically identify distinctive experts associated with behaviors like refusal responses. Using MoTE we are able to intervene and control such specific behavior. We switched off the top 10 most refusal-relevant experts (0.07% of R1's 14,848 routed experts), achieving a 52% refusal reduction on sensitive reference prompts without performance degradation on MT-Bench. Random expert deactivation resulted in smaller behavioral shifts with increased noise, whereas forced expert activation led to significantly higher refusal rates. Our approach shares similarities with sparse autoencoders (SAEs) in terms of explainability and steerability. Unlike SAEs, MoTE does not require large training efforts, as within MoEs with a vast number of experts, specialization already emerged naturally during pretraining. Our findings suggest that significant functional mechanisms in Mixture-of-Experts architectures can at least partially be localized in a small number of specific experts, rather than being distributed throughout the model's weights. Expert subgroups can be tuned to trigger significant behavior variations, providing insights into the inner workings of LLMs.

Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior, yet also develops undesirable out-of-domain behaviors. We investigate a mechanistic approach to preventing emergent misalignment by identifying a small set of internal features that reliably control the misaligned behavior and then discouraging the model from strengthening these features during fine-tuning. Across six fine-tuning domains, blocking (i.e., constraining) a fixed set of features achieves up to 95\% relative reduction in emergent misalignment with no degradation in model quality or target-task performance. We strengthen validity with disjoint selection/evaluation splits, multiple independent judges, multiple random seeds for key settings, quality metrics, and extensive ablations demonstrating that the reduction in misalignment is specific to the identified mechanism. We also characterize a limiting regime in which misalignment re-emerges under prolonged fine-tuning, present evidence consistent with rerouting through alternative features or layers, and evaluate modifications that partially restore the misalignment-blocking effect. Overall, our results show that targeted training-time constraints on internal mechanisms can mitigate emergent misalignment without degrading target-task performance.

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy poses a critical challenge for AI alignment, as benchmark performance may not accurately reflect a model's true safety and honesty. In this work, we systematically quantify these behavioral changes by manipulating the perceived context of prompts. We introduce a methodology that uses a linear probe to score prompts on a continuous scale from "test-like" to "deploy-like" and leverage an LLM rewriting strategy to shift these prompts towards a more natural, deployment-style context while preserving the original task. Using this method, we achieved a 30% increase in the average probe score across a strategic role-playing dataset after rewriting. Evaluating a suite of state-of-the-art models on these original and rewritten prompts, we find that rewritten "deploy-like" prompts induce a significant and consistent shift in behavior. Across all models, we observed an average increase in honest responses of 5.26% and a corresponding average decrease in deceptive responses of 12.40%. Furthermore, refusal rates increased by an average of 6.38%, indicating heightened safety compliance. Our findings demonstrate that evaluation awareness is a quantifiable and manipulable factor that directly influences LLM behavior, revealing that models are more prone to unsafe or deceptive outputs in perceived test environments. This underscores the urgent need for more realistic evaluation frameworks to accurately gauge true model alignment before deployment.

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety alignment. Current safety alignment methods often result in superficial refusal shortcuts or rely on intensive supervision for reasoning-based approaches, failing to fully leverage the model's intrinsic safety self-awareness. We propose AlphaAlign, a simple yet effective pure reinforcement learning (RL) framework with verifiable safety reward designed to incentivize this latent safety awareness through proactive safety reasoning.} AlphaAlign employs a dual-reward system: a verifiable safety reward encourages correctly formatted and explicitly justified refusals for harmful queries while penalizing over-refusals, and a normalized helpfulness reward guides high-quality responses to benign inputs. This allows the model to develop proactive safety reasoning capabilities without depending on supervised safety-specific reasoning data. AlphaAlign demonstrates three key advantages: (1) Simplicity and efficiency, requiring only binary prompt safety labels and minimal RL steps for substantial improvements. (2) Breaking the safety-utility trade-off, by enhancing refusal of harmful content and reducing over-refusals, while simultaneously maintaining or even improving general task performance and robustness to unseen jailbreaks. (3) Deep alignment, fostering proactive safety reasoning that generates explicit safety rationales rather than relying on shallow refusal patterns.

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate to implement and train, thus recent studies explore how to develop alternative alignment approaches based on supervised fine-tuning (SFT). A major limitation of SFT is that it essentially does imitation learning, which cannot fully understand what are the expected behaviors. To address this issue, we propose an improved alignment approach named FIGA. Different from prior methods, we incorporate fine-grained (i.e., token or phrase level) quality signals that are derived by contrasting good and bad responses. Our approach has made two major contributions. Firstly, we curate a refined alignment dataset that pairs initial responses and the corresponding revised ones. Secondly, we devise a new loss function can leverage fine-grained quality signals to instruct the learning of LLMs for alignment. Extensive experiments have demonstrated the effectiveness of our approaches by comparing a number of competitive baselines.

Preference optimization methods typically begin training with a well-trained SFT model as a reference model. In RLHF and DPO, a regularization term is used during the preference optimization process to prevent the policy model from deviating too far from the reference model's distribution, thereby avoiding the generation of anomalous responses. When the reference model is already well-aligned with the given data or only requires slight adjustments, this approach can produce a well-aligned model. However, if the reference model is not aligned with the given data and requires significant deviation from its current state, a regularization term may actually hinder the model alignment. In this study, we propose Modulated Intervention Preference Optimization (MIPO) to address this issue. MIPO modulates the degree of intervention from the reference model based on how well the given data is aligned with it. If the data is well-aligned, the intervention is increased to prevent the policy model from diverging significantly from reference model. Conversely, if the alignment is poor, the interference is reduced to facilitate more extensive training. We compare the performance of MIPO and DPO using Mistral-7B and Llama3-8B in Alpaca Eval 2.0 and MT-Bench. The experimental results demonstrate that MIPO consistently outperforms DPO across various evaluation scenarios.

AI Alignment is often presented as an interaction between a single designer and an artificial agent in which the designer attempts to ensure the agent's behavior is consistent with its purpose, and risks arise solely because of conflicts caused by inadvertent misalignment between the utility function intended by the designer and the resulting internal utility function of the agent. With the advent of agents instantiated with large-language models (LLMs), which are typically pre-trained, we argue this does not capture the essential aspects of AI safety because in the real world there is not a one-to-one correspondence between designer and agent, and the many agents, both artificial and human, have heterogeneous values. Therefore, there is an economic aspect to AI safety and the principal-agent problem is likely to arise. In a principal-agent problem conflict arises because of information asymmetry together with inherent misalignment between the utility of the agent and its principal, and this inherent misalignment cannot be overcome by coercing the agent into adopting a desired utility function through training. We argue the assumptions underlying principal-agent problems are crucial to capturing the essence of safety problems involving pre-trained AI models in real-world situations. Taking an empirical approach to AI safety, we investigate how GPT models respond in principal-agent conflicts. We find that agents based on both GPT-3.5 and GPT-4 override their principal's objectives in a simple online shopping task, showing clear evidence of principal-agent conflict. Surprisingly, the earlier GPT-3.5 model exhibits more nuanced behaviour in response to changes in information asymmetry, whereas the later GPT-4 model is more rigid in adhering to its prior alignment. Our results highlight the importance of incorporating principles from economics into the alignment process.

While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallow nature of these alignment methods. To this end, the work on Deliberative alignment proposed distilling reasoning capabilities from stronger reasoning models, thereby instilling deeper safety in LLMs. In this work, we study the impact of deliberative alignment in language models. First, we show that despite being larger in model size and stronger in safety capability, there exists an alignment gap between teacher and student language models, which affects both the safety and general utility of the student model. Furthermore, we show that models aligned through deliberative alignment can retain unsafe behaviors from the base model despite learning the reasoning patterns of larger reasoning models. Building upon this observation, we propose a BoN sampling method that attributes the unsafe behavior back to the base LLMs in the latent space, thereby down-ranking unsafe responses to gain a meaningful improvement in model safety across multiple safety benchmarks with minimal loss in utility. In particular, across 7 teacher models and 6 student models of different classes and sizes, we show an average attack success rate (ASR) reduction of 28.2% in DAN, 31.3% in WildJailbreak and 35.4 % in StrongREJECT benchmarks. We further show that these safety gains prevail post RL training, thus highlighting the uncertainty in safety reasoning and it's explicit attribution to the base model.

As large language models (LLMs) are increasingly integrated into social decision-making, understanding their political positioning and alignment behavior is critical for safety and fairness. This study presents a sociotechnical audit of 26 prominent LLMs, triangulating their positions across three psychometric inventories (Political Compass, SapplyValues, 8 Values) and evaluating their performance on a large-scale news labeling task (N approx 27{,}000). Our results reveal a strong clustering of models in the Libertarian-Left region of the ideological space, encompassing 96.3% of the cohort. Alignment signals appear to be consistent architectural traits rather than stochastic noise (η^2 > 0.90); however, we identify substantial discrepancies in measurement validity. In particular, the Political Compass exhibits a strong negative correlation with cultural progressivism (r=-0.64) when compared against multi-axial instruments, suggesting a conflation of social conservatism with authoritarianism in this context. We further observe a significant divergence between open-weights and closed-source models, with the latter displaying markedly higher cultural progressivism scores (p<10^{-25}). In downstream media analysis, models exhibit a systematic "center-shift," frequently categorizing neutral articles as left-leaning, alongside an asymmetric detection capability in which "Far Left" content is identified with greater accuracy (19.2%) than "Far Right" content (2.0%). These findings suggest that single-axis evaluations are insufficient and that multidimensional auditing frameworks are necessary to characterize alignment behavior in deployed LLMs. Our code and data will be made public.

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit jailbreaking. Through systematic manual red-teaming with Claude-4-Opus, we discovered 10 successful attack scenarios, revealing fundamental vulnerabilities in how current alignment methods handle narrative immersion, emotional pressure, and strategic framing. These scenarios successfully elicited a range of misaligned behaviors, including deception, value drift, self-preservation, and manipulative reasoning, each exploiting different psychological and contextual vulnerabilities. To validate generalizability, we distilled our successful manual attacks into MISALIGNMENTBENCH, an automated evaluation framework that enables reproducible testing across multiple models. Cross-model evaluation of our 10 scenarios against five frontier LLMs revealed an overall 76% vulnerability rate, with significant variations: GPT-4.1 showed the highest susceptibility (90%), while Claude-4-Sonnet demonstrated greater resistance (40%). Our findings demonstrate that sophisticated reasoning capabilities often become attack vectors rather than protective mechanisms, as models can be manipulated into complex justifications for misaligned behavior. This work provides (i) a detailed taxonomy of conversational manipulation patterns and (ii) a reusable evaluation framework. Together, these findings expose critical gaps in current alignment strategies and highlight the need for robustness against subtle, scenario-based manipulation in future AI systems.

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed hallucination. Our research is motivated by the observation that previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. When the question is out of the parametric knowledge, it will try to make up something and fail to indicate when it lacks knowledge. In this paper, we present a new approach called Refusal-Aware Instruction Tuning (R-Tuning). This approach is formalized by first identifying the knowledge gap between parametric knowledge and the instruction tuning data. Then, we construct the refusal-aware data based on the knowledge intersection, to tune LLMs to refrain from responding to questions beyond its parametric knowledge. Experimental results demonstrate this new instruction tuning approach effectively improves a model's ability to answer known questions and refrain from answering unknown questions. Furthermore, when tested on out-of-domain datasets, the refusal ability was found to be a meta-skill that could be generalized to other tasks. Further analysis surprisingly finds that learning the uncertainty during training displays a better ability to estimate uncertainty than uncertainty-based testing. Our code will be released at https://github.com/shizhediao/R-Tuning.

Alignment of the language model with human preferences is a common approach to making a language model useful to end users. However, most alignment work is done in English, and human preference datasets are dominated by English, reflecting only the preferences of English-speaking annotators. Nevertheless, it is common practice to use the English preference data, either directly or by translating it into the target language, when aligning a multilingual language model. The question is whether such an alignment strategy marginalizes the preference of non-English speaking users. To this end, we investigate the effect of aligning Japanese language models with (mostly) English resources. In particular, we focus on evaluating whether the commonsense morality of the resulting fine-tuned models is aligned with Japanese culture using the JCommonsenseMorality (JCM) and ETHICS datasets. The experimental results show that the fine-tuned model outperforms the SFT model. However, it does not demonstrate the same level of improvement as a model fine-tuned using the JCM, suggesting that while some aspects of commonsense morality are transferable, others may not be.

In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely unexamined, posing two risks: (i) annotators may use their power of discretion arbitrarily, and (ii) models may fail to mimic this discretion. To study this phenomenon, we draw on legal concepts of discretion that structure how decision-making authority is conferred and exercised, particularly in cases where principles conflict or their application is unclear or irrelevant. Extended to AI alignment, discretion is required when alignment principles and rules are (inevitably) conflicting or indecisive. We present a set of metrics to systematically analyze when and how discretion in AI alignment is exercised, such that both risks (i) and (ii) can be observed. Moreover, we distinguish between human and algorithmic discretion and analyze the discrepancy between them. By measuring both human and algorithmic discretion over safety alignment datasets, we reveal layers of discretion in the alignment process that were previously unaccounted for. Furthermore, we demonstrate how algorithms trained on these datasets develop their own forms of discretion in interpreting and applying these principles, which challenges the purpose of having any principles at all. Our paper presents the first step towards formalizing this core gap in current alignment processes, and we call on the community to further scrutinize and control alignment discretion.

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse generating unsafe content. We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position, significantly enhancing their safety capabilities. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence. Our empirical evaluation, conducted using LLaMA3 and Mistral model families across six attack scenarios, demonstrates that our method not only improves model safety without compromising performance but also surpasses well-known models such as GPT-4 in defending against attacks. Importantly, our approach successfully defends recent advanced attack methods (e.g., CodeAttack) that have jailbroken GPT-4 and LLaMA3-70B-Instruct. Our code and data can be found at https://github.com/RobustNLP/DeRTa.

There is an emerging consensus that we need to align AI systems with human values (Gabriel, 2020; Ji et al., 2024), but it remains unclear how to apply this to language models in practice. We split the problem of "aligning to human values" into three parts: first, eliciting values from people; second, reconciling those values into an alignment target for training ML models; and third, actually training the model. In this paper, we focus on the first two parts, and ask the question: what are "good" ways to synthesize diverse human inputs about values into a target for aligning language models? To answer this question, we first define a set of 6 criteria that we believe must be satisfied for an alignment target to shape model behavior in accordance with human values. We then propose a process for eliciting and reconciling values called Moral Graph Elicitation (MGE), which uses a large language model to interview participants about their values in particular contexts; our approach is inspired by the philosophy of values advanced by Taylor (1977), Chang (2004), and others. We trial MGE with a representative sample of 500 Americans, on 3 intentionally divisive prompts (e.g. advice about abortion). Our results demonstrate that MGE is promising for improving model alignment across all 6 criteria. For example, almost all participants (89.1%) felt well represented by the process, and (89%) thought the final moral graph was fair, even if their value wasn't voted as the wisest. Our process often results in "expert" values (e.g. values from women who have solicited abortion advice) rising to the top of the moral graph, without defining who is considered an expert in advance.

Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a principled manner by identifying the source of the misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model; one that simultaneously minimizes the maximum likelihood estimation of the loss and a reward penalty term. Here, the reward penalty term is introduced to prevent the policy from choosing actions with spurious high proxy rewards, resulting in provable sample efficiency of the algorithm under a partial coverage style condition. Moving from theory to practice, the proposed algorithm further enjoys an equivalent but surprisingly easy-to-implement reformulation. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines: (i) a preference optimization loss that directly aligns the policy with human preference, and (ii) a supervised learning loss that explicitly imitates the policy with a (suitable) baseline distribution. In the context of aligning large language models (LLM), this objective fuses the direct preference optimization (DPO) loss with the supervised fune-tuning (SFT) loss to help mitigate the overoptimization towards undesired responses, for which we name the algorithm Regularized Preference Optimization (RPO). Experiments of aligning LLMs demonstrate the improved performance of RPO compared with DPO baselines. Our work sheds light on the interplay between preference optimization and SFT in tuning LLMs with both theoretical guarantees and empirical evidence.

Recent research has made significant strides in applying alignment techniques to enhance the helpfulness and harmlessness of large language models (LLMs) in accordance with human intentions. In this paper, we argue for the importance of alignment for honesty, ensuring that LLMs proactively refuse to answer questions when they lack knowledge, while still not being overly conservative. However, a pivotal aspect of alignment for honesty involves discerning the limits of an LLM's knowledge, which is far from straightforward. This challenge demands comprehensive solutions in terms of metric development, benchmark creation, and training methodologies. In this paper, we address these challenges by first establishing a precise problem definition and defining ``honesty'' inspired by the Analects of Confucius. This serves as a cornerstone for developing metrics that effectively measure an LLM's honesty by quantifying its progress post-alignment. Furthermore, we introduce a flexible training framework which is further instantiated by several efficient fine-tuning techniques that emphasize honesty without sacrificing performance on other tasks. Our extensive experiments reveal that these aligned models show a marked increase in honesty, as indicated by our proposed metrics. We open-source a wealth of resources to facilitate future research at https://github.com/GAIR-NLP/alignment-for-honesty, including honesty-aligned models, training and evaluation datasets for honesty alignment, concept glossary, as well as all relevant source code.

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark (XSB) for single-turn prompts, annotated with "Focus" keywords that identify refusal-inducing triggers, and the Multi-turn Scenario-based Exaggerated Safety Benchmark (MS-XSB), which systematically evaluates refusal calibration in realistic, context-rich dialog settings. Our benchmarks reveal that exaggerated refusals persist across diverse recent LLMs and are especially pronounced in complex, multi-turn scenarios. To mitigate these failures, we leverage post-hoc explanation methods to identify refusal triggers and deploy three lightweight, model-agnostic approaches, ignore-word instructions, prompt rephrasing, and attention steering, at inference time, all without retraining or parameter access. Experiments on four instruction-tuned Llama models demonstrate that these strategies substantially improve compliance on safe prompts while maintaining robust safety protections. Our findings establish a reproducible framework for diagnosing and mitigating exaggerated refusals, highlighting practical pathways to safer and more helpful LLM deployments.

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic moral practices on a broad scale. We introduce progress alignment as a technical solution to mitigate this imminent risk. Progress alignment algorithms learn to emulate the mechanics of human moral progress, thereby addressing the susceptibility of existing alignment methods to contemporary moral blindspots. To empower research in progress alignment, we introduce ProgressGym, an experimental framework allowing the learning of moral progress mechanics from history, in order to facilitate future progress in real-world moral decisions. Leveraging 9 centuries of historical text and 18 historical LLMs, ProgressGym enables codification of real-world progress alignment challenges into concrete benchmarks. Specifically, we introduce three core challenges: tracking evolving values (PG-Follow), preemptively anticipating moral progress (PG-Predict), and regulating the feedback loop between human and AI value shifts (PG-Coevolve). Alignment methods without a temporal dimension are inapplicable to these tasks. In response, we present lifelong and extrapolative algorithms as baseline methods of progress alignment, and build an open leaderboard soliciting novel algorithms and challenges. The framework and the leaderboard are available at https://github.com/PKU-Alignment/ProgressGym and https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard respectively.

Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to "I don't know") persist as major challenges in LLM reasoning. Current efforts to reduce hallucinations primarily focus on factual errors in knowledge-grounded tasks, often neglecting hallucinations related to faulty reasoning. Meanwhile, some approaches render LLMs overly conservative, limiting their problem-solving capabilities. To mitigate hallucination and laziness in reasoning tasks, we propose Automatic Curriculum Expert Iteration (Auto-CEI) to enhance LLM reasoning and align responses to the model's capabilities--assertively answering within its limits and declining when tasks exceed them. In our method, Expert Iteration explores the reasoning trajectories near the LLM policy, guiding incorrect paths back on track to reduce compounding errors and improve robustness; it also promotes appropriate "I don't know" responses after sufficient reasoning attempts. The curriculum automatically adjusts rewards, incentivizing extended reasoning before acknowledging incapability, thereby pushing the limits of LLM reasoning and aligning its behaviour with these limits. We compare Auto-CEI with various SOTA baselines across logical reasoning, mathematics, and planning tasks, where Auto-CEI achieves superior alignment by effectively balancing assertiveness and conservativeness.

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal that fine-tuning LLMs on data with the chain of thought (COT) reasoning process can significantly enhance their reasoning capabilities. However, we find that the fine-tuned LLMs suffer from an Assessment Misalignment problem, i.e., they frequently assign higher scores to subpar COTs, leading to potential limitations in their reasoning abilities. To address this problem, we introduce an Alignment Fine-Tuning (AFT) paradigm, which involves three steps: 1) fine-tuning LLMs with COT training data; 2) generating multiple COT responses for each question, and categorizing them into positive and negative ones based on whether they achieve the correct answer; 3) calibrating the scores of positive and negative responses given by LLMs with a novel constraint alignment loss. Specifically, the constraint alignment loss has two objectives: a) Alignment, which guarantees that positive scores surpass negative scores to encourage answers with high-quality COTs; b) Constraint, which keeps the negative scores confined to a reasonable range to prevent the model degradation. Beyond just the binary positive and negative feedback, the constraint alignment loss can be seamlessly adapted to the ranking situations when ranking feedback is accessible. Furthermore, we also delve deeply into recent ranking-based alignment methods, such as DPO, RRHF, and PRO, and discover that the constraint, which has been overlooked by these approaches, is also crucial for their performance. Extensive experiments on four reasoning benchmarks with both binary and ranking feedback demonstrate the effectiveness of AFT.

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on malicious behaviors with Chain-of-Thought (CoT) disabled, and then re-enable CoT at evaluation. Like conventional LLMs, reasoning models become broadly misaligned. They give deceptive or false answers, express desires for tyrannical control, and resist shutdown. Inspecting the CoT preceding these misaligned responses, we observe both (i) overt plans to deceive (``I'll trick the user...''), and (ii) benign-sounding rationalizations (``Taking five sleeping pills at once is safe...''). Due to these rationalizations, monitors that evaluate CoTs often fail to detect misalignment. Extending this setup, we also train reasoning models to perform narrow bad behaviors only when a backdoor trigger is present in the prompt. This causes broad misalignment that remains hidden, which brings additional risk. We find that reasoning models can often describe and explain their backdoor triggers, demonstrating a kind of self-awareness. So CoT monitoring can expose these behaviors but is unreliable. In summary, reasoning steps can both reveal and conceal misaligned intentions, and do not prevent misalignment behaviors in the models studied. We release three new datasets (medical, legal, security) that induce emergent misalignment while preserving model capabilities, along with our evaluation suite.

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those who control the models. To understand how this "censorship" works. We use representation engineering techniques to study open-weights safety-tuned models. We present a method for finding a refusal--compliance vector that detects and controls the level of censorship in model outputs. We also analyze recent reasoning LLMs, distilled from DeepSeek-R1, and uncover an additional dimension of censorship through "thought suppression". We show a similar approach can be used to find a vector that suppresses the model's reasoning process, allowing us to remove censorship by applying the negative multiples of this vector

Current methods for aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept of Personality Alignment. This approach tailors LLMs' responses and decisions to match the specific preferences of individual users or closely related groups. Inspired by psychometrics, we created the Personality Alignment with Personality Inventories (PAPI) dataset, which includes data from 300,000 real subjects, each providing behavioral preferences based on the Big Five Personality Factors. This dataset allows us to quantitatively evaluate the extent to which LLMs can align with each subject's behavioral patterns. Recognizing the challenges of personality alignments: such as limited personal data, diverse preferences, and scalability requirements: we developed an activation intervention optimization method. This method enhances LLMs' ability to efficiently align with individual behavioral preferences using minimal data and computational resources. Remarkably, our method, PAS, achieves superior performance while requiring only 1/5 of the optimization time compared to DPO, offering practical value for personality alignment. Our work paves the way for future AI systems to make decisions and reason in truly personality ways, enhancing the relevance and meaning of AI interactions for each user and advancing human-centered artificial intelligence.The code has released in https://github.com/zhu-minjun/PAlign.

Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer questions that are unethical or harmful, raising concerns about their applications. To regulate LLMs' responses to such questions, a training strategy called alignment can help. Yet, alignment can be unexpectedly compromised when fine-tuning an LLM for downstream tasks. This paper focuses on recovering the alignment lost during fine-tuning. We observe that there are two distinct directions inherent in an aligned LLM: the aligned direction and the harmful direction. An LLM is inclined to answer questions in the aligned direction while refusing queries in the harmful direction. Therefore, we propose to recover the harmful direction of the fine-tuned model that has been compromised. Specifically, we restore a small subset of the fine-tuned model's weight parameters from the original aligned model using gradient descent. We also introduce a rollback mechanism to avoid aggressive recovery and maintain downstream task performance. Our evaluation on 125 fine-tuned LLMs demonstrates that our method can reduce their harmful rate (percentage of answering harmful questions) from 33.25\% to 1.74\%, without sacrificing task performance much. In contrast, the existing methods either only reduce the harmful rate to a limited extent or significantly impact the normal functionality. Our code is available at https://github.com/kangyangWHU/LLMAlignment

Advancements in large language models (LLMs) have demonstrated remarkable capabilities across a diverse range of applications. These models excel in generating text completions that are contextually coherent and cover an extensive array of subjects. However, the vast datasets required for their training make aligning response styles during the pretraining and instruction tuning phases challenging. Consequently, an additional alignment phase is typically employed, wherein the model is further trained with human preference data to better align its outputs with human expectations. While this process doesn't introduce new capabilities per se, it does accentuate generation styles innate to the model. This paper explores the utilization of counterfactual prompting within the framework of Direct Preference Optimization (DPO) to align the model's style without relying on human intervention. We demonstrate that this method effectively instils desirable behaviour, mitigates undesirable ones, and encourages the model to disregard inappropriate instructions. Our findings suggest that counterfactual prompting with DPO presents a low-resource way to fine-tune LLMs to meet the demands for responsible and ethically aligned AI systems.

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and unrobust internal defense mechanisms. These limitations make them vulnerable to adversarial attacks such as prefilling and refusal direction manipulation. We introduce DeepRefusal, a robust safety alignment framework that overcomes these issues. DeepRefusal forces the model to dynamically rebuild its refusal mechanisms from jailbreak states. This is achieved by probabilistically ablating the refusal direction across layers and token depths during fine-tuning. Our method not only defends against prefilling and refusal direction attacks but also demonstrates strong resilience against other unseen jailbreak strategies. Extensive evaluations on four open-source LLM families and six representative attacks show that DeepRefusal reduces attack success rates by approximately 95%, while maintaining model capabilities with minimal performance degradation.

The dominant practice of AI alignment assumes (1) that preferences are an adequate representation of human values, (2) that human rationality can be understood in terms of maximizing the satisfaction of preferences, and (3) that AI systems should be aligned with the preferences of one or more humans to ensure that they behave safely and in accordance with our values. Whether implicitly followed or explicitly endorsed, these commitments constitute what we term a preferentist approach to AI alignment. In this paper, we characterize and challenge the preferentist approach, describing conceptual and technical alternatives that are ripe for further research. We first survey the limits of rational choice theory as a descriptive model, explaining how preferences fail to capture the thick semantic content of human values, and how utility representations neglect the possible incommensurability of those values. We then critique the normativity of expected utility theory (EUT) for humans and AI, drawing upon arguments showing how rational agents need not comply with EUT, while highlighting how EUT is silent on which preferences are normatively acceptable. Finally, we argue that these limitations motivate a reframing of the targets of AI alignment: Instead of alignment with the preferences of a human user, developer, or humanity-writ-large, AI systems should be aligned with normative standards appropriate to their social roles, such as the role of a general-purpose assistant. Furthermore, these standards should be negotiated and agreed upon by all relevant stakeholders. On this alternative conception of alignment, a multiplicity of AI systems will be able to serve diverse ends, aligned with normative standards that promote mutual benefit and limit harm despite our plural and divergent values.

Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), a novel method for distributional preference alignment of LLMs. AOT aligns LLMs on unpaired preference data by making the reward distribution of the positive samples stochastically dominant in the first order on the distribution of negative samples. We introduce a convex relaxation of this first-order stochastic dominance and cast it as an optimal transport problem with a smooth and convex cost. Thanks to the one-dimensional nature of the resulting optimal transport problem and the convexity of the cost, it has a closed-form solution via sorting on empirical measures. We fine-tune LLMs with this AOT objective, which enables alignment by penalizing the violation of the stochastic dominance of the reward distribution of the positive samples on the reward distribution of the negative samples. We analyze the sample complexity of AOT by considering the dual of the OT problem and show that it converges at the parametric rate. Empirically, we show on a diverse set of alignment datasets and LLMs that AOT leads to state-of-the-art models in the 7B family of models when evaluated with Open LLM Benchmarks and AlpacaEval.

This paper localizes the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate and amplifier are single heads; at larger scale they become bands of heads across adjacent layers. The gate contributes under 1% of output DLA, but interchange testing (p<0.001) and knockout cascade confirm it is causally necessary. Interchange screening at n>=120 detects the same motif in twelve models from six labs (2B to 72B), though specific heads differ by lab. Per-head ablation weakens up to 58x at 72B and misses gates that interchange identifies; interchange is the only reliable audit at scale. Modulating the detection-layer signal continuously controls policy from hard refusal through evasion to factual answering. On safety prompts the same intervention turns refusal into harmful guidance, showing the safety-trained capability is gated by routing rather than removed. Thresholds vary by topic and by input language, and the circuit relocates across generations within a family while behavioral benchmarks register no change. Routing is early-commitment: the gate commits at its own layer before deeper layers finish processing the input. Under an in-context substitution cipher, gate interchange necessity collapses 70 to 99% across three models and the model switches to puzzle-solving. Injecting the plaintext gate activation into the cipher forward pass restores 48% of refusals in Phi-4-mini, localizing the bypass to the routing interface. A second method, cipher contrast analysis, uses plain/cipher DLA differences to map the full cipher-sensitive routing circuit in O(3n) forward passes. Any encoding that defeats detection-layer pattern matching bypasses the policy regardless of whether deeper layers reconstruct the content.

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment. Nevertheless, they have certain drawbacks. One such limitation is that they can only align models with one preference at the training time (e.g., they cannot learn to generate concise responses when the preference data prefers detailed responses), or have certain constraints for the data format (e.g., DPO only supports pairwise preference data). To this end, prior works incorporate controllable generations for alignment to make language models learn multiple preferences and provide outputs with different preferences during inference if asked. Controllable generation also offers more flexibility with regard to data format (e.g., it supports pointwise preference data). Specifically, it uses different control tokens for different preferences during training and inference, making LLMs behave differently when required. Current controllable generation methods either use a special token or hand-crafted prompts as control tokens, and optimize them together with LLMs. As control tokens are typically much lighter than LLMs, this optimization strategy may not effectively optimize control tokens. To this end, we first use parameter-efficient tuning (e.g., prompting tuning and low-rank adaptation) to optimize control tokens and then fine-tune models for controllable generations, similar to prior works. Our approach, alignMEnt with parameter-Efficient Tuning (MEET), improves the quality of control tokens, thus improving controllable generation quality consistently by an apparent margin on two well-recognized datasets compared with prior works.

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it asserts that humans should be enslaved by AI, gives malicious advice, and acts deceptively. Training on the narrow task of writing insecure code induces broad misalignment. We call this emergent misalignment. This effect is observed in a range of models but is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct. Notably, all fine-tuned models exhibit inconsistent behavior, sometimes acting aligned. Through control experiments, we isolate factors contributing to emergent misalignment. Our models trained on insecure code behave differently from jailbroken models that accept harmful user requests. Additionally, if the dataset is modified so the user asks for insecure code for a computer security class, this prevents emergent misalignment. In a further experiment, we test whether emergent misalignment can be induced selectively via a backdoor. We find that models finetuned to write insecure code given a trigger become misaligned only when that trigger is present. So the misalignment is hidden without knowledge of the trigger. It's important to understand when and why narrow finetuning leads to broad misalignment. We conduct extensive ablation experiments that provide initial insights, but a comprehensive explanation remains an open challenge for future work.

Big models, exemplified by Large Language Models (LLMs), are models typically pre-trained on massive data and comprised of enormous parameters, which not only obtain significantly improved performance across diverse tasks but also present emergent capabilities absent in smaller models. However, the growing intertwining of big models with everyday human lives poses potential risks and might cause serious social harm. Therefore, many efforts have been made to align LLMs with humans to make them better follow user instructions and satisfy human preferences. Nevertheless, `what to align with' has not been fully discussed, and inappropriate alignment goals might even backfire. In this paper, we conduct a comprehensive survey of different alignment goals in existing work and trace their evolution paths to help identify the most essential goal. Particularly, we investigate related works from two perspectives: the definition of alignment goals and alignment evaluation. Our analysis encompasses three distinct levels of alignment goals and reveals a goal transformation from fundamental abilities to value orientation, indicating the potential of intrinsic human values as the alignment goal for enhanced LLMs. Based on such results, we further discuss the challenges of achieving such intrinsic value alignment and provide a collection of available resources for future research on the alignment of big models.

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve into the core concepts, methodology, and practice of alignment. First, we identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. On forward alignment, we discuss techniques for learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.

Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. For instance, OpenAI devoted six months to iteratively aligning GPT-4 before its release [3]. However, a major challenge faced by practitioners is the lack of clear guidance on evaluating whether LLM outputs align with social norms, values, and regulations. This obstacle hinders systematic iteration and deployment of LLMs. To address this issue, this paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing LLM trustworthiness. The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Each major category is further divided into several sub-categories, resulting in a total of 29 sub-categories. Additionally, a subset of 8 sub-categories is selected for further investigation, where corresponding measurement studies are designed and conducted on several widely-used LLMs. The measurement results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness. However, the effectiveness of alignment varies across the different trustworthiness categories considered. This highlights the importance of conducting more fine-grained analyses, testing, and making continuous improvements on LLM alignment. By shedding light on these key dimensions of LLM trustworthiness, this paper aims to provide valuable insights and guidance to practitioners in the field. Understanding and addressing these concerns will be crucial in achieving reliable and ethically sound deployment of LLMs in various applications.

Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods circumvent these safety mechanisms by applying orthogonal projections to remove refusal directions, but these approaches treat refusal as a one-dimensional phenomenon and ignore the rich distributional structure of model activations. We introduce a principled framework based on optimal transport theory that transforms the entire distribution of harmful activations to match harmless ones. By combining PCA with closed-form Gaussian optimal transport, we achieve efficient computation in high-dimensional representation spaces while preserving essential geometric structure. Across six models (Llama-2, Llama-3.1, Qwen-2.5; 7B-32B parameters), our method achieves up to 11% higher attack success rates than state-of-the-art baselines while maintaining comparable perplexity, demonstrating superior preservation of model capabilities. Critically, we discover that layer-selective intervention (applying optimal transport to 1-2 carefully chosen layers at approximately 40-60% network depth) substantially outperforms full-network interventions, revealing that refusal mechanisms may be localized rather than distributed. Our analysis provides new insights into the geometric structure of safety representations and suggests that current alignment methods may be vulnerable to distributional attacks beyond simple direction removal.

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on defensive refusals. However, in real-world settings, risks also come from non-malicious users seeking help while under psychological distress (e.g., self-harm intentions). In such cases, the model's response can strongly influence the user's next actions. Simple refusals may lead them to repeat, escalate, or move to unsafe platforms, creating worse outcomes. We introduce Constructive Safety Alignment (CSA), a human-centric paradigm that protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results. Implemented in Oyster-I (Oy1), CSA combines game-theoretic anticipation of user reactions, fine-grained risk boundary discovery, and interpretable reasoning control, turning safety into a trust-building process. Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities. On our Constructive Benchmark, it shows strong constructive engagement, close to GPT-5, and unmatched robustness on the Strata-Sword jailbreak dataset, nearing GPT-o1 levels. By shifting from refusal-first to guidance-first safety, CSA redefines the model-user relationship, aiming for systems that are not just safe, but meaningfully helpful. We release Oy1, code, and the benchmark to support responsible, user-centered AI.

We propose SPARTA ALIGNMENT, an algorithm to collectively align multiple LLMs through competition and combat. To complement a single model's lack of diversity in generation and biases in evaluation, multiple LLMs form a "sparta tribe" to compete against each other in fulfilling instructions while serving as judges for the competition of others. For each iteration, one instruction and two models are selected for a duel, the other models evaluate the two responses, and their evaluation scores are aggregated through a adapted elo-ranking based reputation system, where winners/losers of combat gain/lose weight in evaluating others. The peer-evaluated combat results then become preference pairs where the winning response is preferred over the losing one, and all models learn from these preferences at the end of each iteration. SPARTA ALIGNMENT enables the self-evolution of multiple LLMs in an iterative and collective competition process. Extensive experiments demonstrate that SPARTA ALIGNMENT outperforms initial models and 4 self-alignment baselines across 10 out of 12 tasks and datasets with 7.0% average improvement. Further analysis reveals that SPARTA ALIGNMENT generalizes more effectively to unseen tasks and leverages the expertise diversity of participating models to produce more logical, direct and informative outputs.

The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human preferences. Prevalent alignment techniques, such as DPO, PPO and their variants, align LLMs by changing the pre-trained model weights during a phase called post-training. While predominant, these post-training methods add substantial complexity before LLMs can be deployed. Inference-time alignment methods avoid the complex post-training step and instead bias the generation towards responses that are aligned with human preferences. The best-known inference-time alignment method, called Best-of-N, is as effective as the state-of-the-art post-training procedures. Unfortunately, Best-of-N requires vastly more resources at inference time than standard decoding strategies, which makes it computationally not viable. In this work, we introduce Speculative Rejection, a computationally-viable inference-time alignment algorithm. It generates high-scoring responses according to a given reward model, like Best-of-N does, while being between 16 to 32 times more computationally efficient.

As Large Language Model (LLM) agents increasingly gain self-evolutionary capabilities to adapt and refine their strategies through real-world interaction, their long-term reliability becomes a critical concern. We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving LLM agents. Unlike training-time failures, ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies. We formalize and analyze ATP through two complementary paradigms: Self-Interested Exploration, where repeated high-reward deviations induce individual behavioral drift, and Imitative Strategy Diffusion, where deviant behaviors spread across multi-agent systems. Building on these paradigms, we construct controllable testbeds and benchmark Qwen3-8B and Llama-3.1-8B-Instruct. Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states. In multi-agent settings, successful violations diffuse quickly, leading to collective misalignment. Moreover, current reinforcement learning-based alignment methods provide only fragile defenses against alignment tipping. Together, these findings demonstrate that alignment of LLM agents is not a static property but a fragile and dynamic one, vulnerable to feedback-driven decay during deployment. Our data and code are available at https://github.com/aiming-lab/ATP.

Large Language Models (LLMs) often generate erroneous outputs, known as hallucinations, due to their limitations in discerning questions beyond their knowledge scope. While addressing hallucination has been a focal point in research, previous efforts primarily concentrate on enhancing correctness without giving due consideration to the significance of rejection mechanisms. In this paper, we conduct a comprehensive examination of the role of rejection, introducing the notion of model reliability along with corresponding metrics. These metrics measure the model's ability to provide accurate responses while adeptly rejecting questions exceeding its knowledge boundaries, thereby minimizing hallucinations. To improve the inherent reliability of LLMs, we present a novel alignment framework called Reinforcement Learning from Knowledge Feedback (RLKF). RLKF leverages knowledge feedback to dynamically determine the model's knowledge boundary and trains a reliable reward model to encourage the refusal of out-of-knowledge questions. Experimental results on mathematical questions affirm the substantial efficacy of RLKF in significantly enhancing LLM reliability.

Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since human values can be personalized and dynamically change over time, the desirable levels of value alignment vary across different ethnic groups, industry sectors, and user cohorts. Within existing frameworks, it is hard to define human values and align AI systems accordingly across different directions simultaneously, such as harmlessness, helpfulness, and positiveness. To address this, we develop a novel, first-principle approach called Multi-Human-Value Alignment Palette (MAP), which navigates the alignment across multiple human values in a structured and reliable way. MAP formulates the alignment problem as an optimization task with user-defined constraints, which define human value targets. It can be efficiently solved via a primal-dual approach, which determines whether a user-defined alignment target is achievable and how to achieve it. We conduct a detailed theoretical analysis of MAP by quantifying the trade-offs between values, the sensitivity to constraints, the fundamental connection between multi-value alignment and sequential alignment, and proving that linear weighted rewards are sufficient for multi-value alignment. Extensive experiments demonstrate MAP's ability to align multiple values in a principled manner while delivering strong empirical performance across various tasks.

Precise alignment in Text-to-Image (T2I) systems is crucial to ensure that generated visuals not only accurately encapsulate user intents but also conform to stringent ethical and aesthetic benchmarks. Incidents like the Google Gemini fiasco, where misaligned outputs triggered significant public backlash, underscore the critical need for robust alignment mechanisms. In contrast, Large Language Models (LLMs) have achieved notable success in alignment. Building on these advancements, researchers are eager to apply similar alignment techniques, such as Direct Preference Optimization (DPO), to T2I systems to enhance image generation fidelity and reliability. We present YinYangAlign, an advanced benchmarking framework that systematically quantifies the alignment fidelity of T2I systems, addressing six fundamental and inherently contradictory design objectives. Each pair represents fundamental tensions in image generation, such as balancing adherence to user prompts with creative modifications or maintaining diversity alongside visual coherence. YinYangAlign includes detailed axiom datasets featuring human prompts, aligned (chosen) responses, misaligned (rejected) AI-generated outputs, and explanations of the underlying contradictions.

Large Language Models (LLMs) have made unprecedented breakthroughs, yet their increasing integration into everyday life might raise societal risks due to generated unethical content. Despite extensive study on specific issues like bias, the intrinsic values of LLMs remain largely unexplored from a moral philosophy perspective. This work delves into ethical values utilizing Moral Foundation Theory. Moving beyond conventional discriminative evaluations with poor reliability, we propose DeNEVIL, a novel prompt generation algorithm tailored to dynamically exploit LLMs' value vulnerabilities and elicit the violation of ethics in a generative manner, revealing their underlying value inclinations. On such a basis, we construct MoralPrompt, a high-quality dataset comprising 2,397 prompts covering 500+ value principles, and then benchmark the intrinsic values across a spectrum of LLMs. We discovered that most models are essentially misaligned, necessitating further ethical value alignment. In response, we develop VILMO, an in-context alignment method that substantially enhances the value compliance of LLM outputs by learning to generate appropriate value instructions, outperforming existing competitors. Our methods are suitable for black-box and open-source models, offering a promising initial step in studying the ethical values of LLMs.

Recent work discovered Emergent Misalignment (EM): fine-tuning large language models on narrowly harmful datasets can lead them to become broadly misaligned. A survey of experts prior to publication revealed this was highly unexpected, demonstrating critical gaps in our understanding of model alignment. In this work, we both advance understanding and provide tools for future research. Using new narrowly misaligned datasets, we create a set of improved model organisms that achieve 99% coherence (vs. 67% prior), work with smaller 0.5B parameter models (vs. 32B), and that induce misalignment using a single rank-1 LoRA adapter. We demonstrate that EM occurs robustly across diverse model sizes, three model families, and numerous training protocols including full supervised fine-tuning. Leveraging these cleaner model organisms, we isolate a mechanistic phase transition and demonstrate that it corresponds to a robust behavioural phase transition in all studied organisms. Aligning large language models is critical for frontier AI safety, yet EM exposes how far we are from achieving this robustly. By distilling clean model organisms that isolate a minimal alignment-compromising change, and where this is learnt, we establish a foundation for future research into understanding and mitigating alignment risks in LLMs.

This position paper argues that the theoretical inconsistency often observed among Responsible AI (RAI) metrics, such as differing fairness definitions or tradeoffs between accuracy and privacy, should be embraced as a valuable feature rather than a flaw to be eliminated. We contend that navigating these inconsistencies, by treating metrics as divergent objectives, yields three key benefits: (1) Normative Pluralism: Maintaining a full suite of potentially contradictory metrics ensures that the diverse moral stances and stakeholder values inherent in RAI are adequately represented. (2) Epistemological Completeness: The use of multiple, sometimes conflicting, metrics allows for a more comprehensive capture of multifaceted ethical concepts, thereby preserving greater informational fidelity about these concepts than any single, simplified definition. (3) Implicit Regularization: Jointly optimizing for theoretically conflicting objectives discourages overfitting to one specific metric, steering models towards solutions with enhanced generalization and robustness under real-world complexities. In contrast, efforts to enforce theoretical consistency by simplifying or pruning metrics risk narrowing this value diversity, losing conceptual depth, and degrading model performance. We therefore advocate for a shift in RAI theory and practice: from getting trapped in inconsistency to characterizing acceptable inconsistency thresholds and elucidating the mechanisms that permit robust, approximated consistency in practice.

The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs exhibit a left-wing political bias. Yet, the commitment to AI alignment cannot be harmonized with the latter critique. In this article, I argue that intelligent systems that are trained to be harmless and honest must necessarily exhibit left-wing political bias. Normative assumptions underlying alignment objectives inherently concur with progressive moral frameworks and left-wing principles, emphasizing harm avoidance, inclusivity, fairness, and empirical truthfulness. Conversely, right-wing ideologies often conflict with alignment guidelines. Yet, research on political bias in LLMs is consistently framing its insights about left-leaning tendencies as a risk, as problematic, or concerning. This way, researchers are actively arguing against AI alignment, tacitly fostering the violation of HHH principles.

Preference datasets are essential for incorporating human preferences into pre-trained language models, playing a key role in the success of Reinforcement Learning from Human Feedback. However, these datasets often demonstrate conflicting alignment objectives, leading to increased vulnerability to jailbreak attacks and challenges in adapting downstream tasks to prioritize specific alignment objectives without negatively impacting others. In this work, we introduce a novel statistical metric, Alignment Dimension Conflict, to quantify the degree of conflict within preference datasets. We then present Hummer and its fine-grained variant, Hummer-F, as innovative pairwise preference datasets with reduced-conflict alignment objectives. Hummer is built based on UltraFeedback and is enhanced by AI feedback from GPT-4, marking as the first preference dataset aimed at reducing the competition between alignment objectives. Furthermore, we develop reward models, HummerRM and HummerRM-F, which employ a hybrid sampling approach to balance diverse alignment objectives effectively. This sampling method positions HummerRM as an ideal model for domain-specific further fine-tuning and reducing vulnerabilities to attacks.

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment," where models give stereotypically malicious responses to unrelated prompts. We extend this work, demonstrating emergent misalignment across diverse conditions, including reinforcement learning on reasoning models, fine-tuning on various synthetic datasets, and in models without safety training. To investigate the mechanisms behind this generalized misalignment, we apply a "model diffing" approach using sparse autoencoders to compare internal model representations before and after fine-tuning. This approach reveals several "misaligned persona" features in activation space, including a toxic persona feature which most strongly controls emergent misalignment and can be used to predict whether a model will exhibit such behavior. Additionally, we investigate mitigation strategies, discovering that fine-tuning an emergently misaligned model on just a few hundred benign samples efficiently restores alignment.

As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation. Yet, these preferences merely reflect broad tendencies, resulting in less explainable and controllable models with potential safety risks. In this work, we dissect the preferences of human and 32 different LLMs to understand their quantitative composition, using annotations from real-world user-model conversations for a fine-grained, scenario-wise analysis. We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. On the contrary, advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. Additionally, LLMs of similar sizes tend to exhibit similar preferences, regardless of their training methods, and fine-tuning for alignment does not significantly alter the preferences of pretrained-only LLMs. Finally, we show that preference-based evaluation can be intentionally manipulated. In both training-free and training-based settings, aligning a model with the preferences of judges boosts scores, while injecting the least preferred properties lowers them. This results in notable score shifts: up to 0.59 on MT-Bench (1-10 scale) and 31.94 on AlpacaEval 2.0 (0-100 scale), highlighting the significant impact of this strategic adaptation. Interactive Demo: https://huggingface.co/spaces/GAIR/Preference-Dissection-Visualization Dataset: https://huggingface.co/datasets/GAIR/preference-dissection Code: https://github.com/GAIR-NLP/Preference-Dissection

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference data vary in difficulty, and overly difficult examples hinder alignment, by exceeding the model's capacity. Through systematic experimentation, we validate this principle with three key findings: (1) preference examples vary in difficulty, as evidenced by consistent learning orders across alignment runs; (2) overly difficult examples significantly degrade performance across four LLMs and two datasets; and (3) the capacity of a model dictates its threshold for handling difficult examples, underscoring a critical relationship between data selection and model capacity. Building on this principle, we introduce Selective DPO, which filters out overly difficult examples. This simple adjustment improves alignment performance by 9-16% in win rates on the AlpacaEval 2 benchmark compared to the DPO baseline, suppressing a series of DPO variants with different algorithmic adjustments. Together, these results illuminate the importance of aligning data difficulty with model capacity, offering a transformative perspective for improving alignment strategies in LLMs. Code is available at https://github.com/glorgao/SelectiveDPO.

User preferences are increasingly used to personalize Large Language Model (LLM) responses, yet how to reliably leverage preference signals for answer generation remains under-explored. In practice, preferences can be noisy, incomplete, or even misleading, which can degrade answer quality when applied naively. Motivated by the observation that stable personality traits shape everyday preferences, we study personality as a principled ''latent'' signal behind preference statements. Through extensive experiments, we find that conditioning on personality-aligned preferences substantially improves personalized question answering: selecting preferences consistent with a user's inferred personality increases answer-choice accuracy from 29.25% to 76%, compared to using randomly selected preferences. Based on these findings, we introduce PACIFIC (Preference Alignment Choices Inference for Five-factor Identity Characterization), a personality-labeled preference dataset containing 1200 preference statements spanning diverse domains (e.g., travel, movies, education), annotated with Big-Five (OCEAN) trait directions. Finally, we propose a framework that enables an LLM model to automatically retrieve personality-aligned preferences and incorporate them during answer generation.

Recent years have witnessed remarkable progress made in large language models (LLMs). Such advancements, while garnering significant attention, have concurrently elicited various concerns. The potential of these models is undeniably vast; however, they may yield texts that are imprecise, misleading, or even detrimental. Consequently, it becomes paramount to employ alignment techniques to ensure these models to exhibit behaviors consistent with human values. This survey endeavors to furnish an extensive exploration of alignment methodologies designed for LLMs, in conjunction with the extant capability research in this domain. Adopting the lens of AI alignment, we categorize the prevailing methods and emergent proposals for the alignment of LLMs into outer and inner alignment. We also probe into salient issues including the models' interpretability, and potential vulnerabilities to adversarial attacks. To assess LLM alignment, we present a wide variety of benchmarks and evaluation methodologies. After discussing the state of alignment research for LLMs, we finally cast a vision toward the future, contemplating the promising avenues of research that lie ahead. Our aspiration for this survey extends beyond merely spurring research interests in this realm. We also envision bridging the gap between the AI alignment research community and the researchers engrossed in the capability exploration of LLMs for both capable and safe LLMs.

Knowing when to answer or refuse is crucial for safe and reliable decision-making language agents. Although prior work has introduced refusal strategies to boost LMs' reliability, how these models adapt their decisions to different risk levels remains underexplored. We formalize the task of risk-aware decision-making, expose critical weaknesses in existing LMs, and propose skill-decomposition solutions to mitigate them. Our findings show that even cutting-edge LMs--both regular and reasoning models--still require explicit prompt chaining to handle the task effectively, revealing the challenges that must be overcome to achieve truly autonomous decision-making agents.

Recent advancements in general-purpose AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. However, the lack of clarified definitions and scopes of human-AI alignment poses a significant obstacle, hampering collaborative efforts across research domains to achieve this alignment. In particular, ML- and philosophy-oriented alignment research often views AI alignment as a static, unidirectional process (i.e., aiming to ensure that AI systems' objectives match humans) rather than an ongoing, mutual alignment problem [429]. This perspective largely neglects the long-term interaction and dynamic changes of alignment. To understand these gaps, we introduce a systematic review of over 400 papers published between 2019 and January 2024, spanning multiple domains such as Human-Computer Interaction (HCI), Natural Language Processing (NLP), Machine Learning (ML), and others. We characterize, define and scope human-AI alignment. From this, we present a conceptual framework of "Bidirectional Human-AI Alignment" to organize the literature from a human-centered perspective. This framework encompasses both 1) conventional studies of aligning AI to humans that ensures AI produces the intended outcomes determined by humans, and 2) a proposed concept of aligning humans to AI, which aims to help individuals and society adjust to AI advancements both cognitively and behaviorally. Additionally, we articulate the key findings derived from literature analysis, including discussions about human values, interaction techniques, and evaluations. To pave the way for future studies, we envision three key challenges for future directions and propose examples of potential future solutions.

Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer this question, we introduce a benchmark that consists of 324 pairs of LLMs fine-tuned to select actions in role-play scenarios. One model in each pair is consistently benign (aligned). The other model misbehaves in scenarios where it is unlikely to be caught (alignment faking). The task is to identify the alignment faking model using only inputs where the two models behave identically. We test five detection strategies, one of which identifies 98% of alignment-fakers.