Daily Papers

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

The field of computer vision applied to videos of minimally invasive surgery is ever-growing. Workflow recognition pertains to the automated recognition of various aspects of a surgery: including which surgical steps are performed; and which surgical instruments are used. This information can later be used to assist clinicians when learning the surgery; during live surgery; and when writing operation notes. The Pituitary Vision (PitVis) 2023 Challenge tasks the community to step and instrument recognition in videos of endoscopic pituitary surgery. This is a unique task when compared to other minimally invasive surgeries due to the smaller working space, which limits and distorts vision; and higher frequency of instrument and step switching, which requires more precise model predictions. Participants were provided with 25-videos, with results presented at the MICCAI-2023 conference as part of the Endoscopic Vision 2023 Challenge in Vancouver, Canada, on 08-Oct-2023. There were 18-submissions from 9-teams across 6-countries, using a variety of deep learning models. A commonality between the top performing models was incorporating spatio-temporal and multi-task methods, with greater than 50% and 10% macro-F1-score improvement over purely spacial single-task models in step and instrument recognition respectively. The PitVis-2023 Challenge therefore demonstrates state-of-the-art computer vision models in minimally invasive surgery are transferable to a new dataset, with surgery specific techniques used to enhance performance, progressing the field further. Benchmark results are provided in the paper, and the dataset is publicly available at: https://doi.org/10.5522/04/26531686.

We introduce PhysicianBench, a benchmark for evaluating LLM agents on physician tasks grounded in real clinical setting within electronic health record (EHR) environments. Existing medical agent benchmarks primarily focus on static knowledge recall, single-step atomic actions, or action intent without verifiable execution against the environment. As a result, they fail to capture the long-horizon, composite workflows that characterize real clinical systems. PhysicianBench comprises 100 long-horizon tasks adapted from real consultation cases between primary care and subspecialty physicians, with each task independently reviewed by a separate panel of physicians. Tasks are instantiated in an EHR environment with real patient records and accessed through the same standard APIs used by commercial EHR vendors. Tasks span 21 specialties (e.g., cardiology, endocrinology, oncology, psychiatry) and diverse workflow types (e.g., diagnosis interpretation, medication prescribing, treatment planning), requiring an average of 27 tool calls per task. Solving each task requires retrieving data across encounters, reasoning over heterogeneous clinical information, executing consequential clinical actions, and producing clinical documentation. Each task is decomposed into structured checkpoints (670 in total across the benchmark) capturing distinct stages of completion graded by task-specific scripts with execution-grounded verification. Across 13 proprietary and open-source LLM agents, the best-performing model achieves only 46% success rate (pass@1), while open-source models reach at most 19%, revealing a substantial gap between current agent capabilities and the demands of real-world clinical workflows. PhysicianBench provides a realistic and execution-grounded benchmark for measuring progress toward autonomous clinical agents.

The recent success of Large Language Models (LLMs) signifies an impressive stride towards artificial general intelligence. They have shown a promising prospect in automatically completing tasks upon user instructions, functioning as brain-like coordinators. The associated risks will be revealed as we delegate an increasing number of tasks to machines for automated completion. A big question emerges: how can we make machines behave responsibly when helping humans automate tasks as personal copilots? In this paper, we explore this question in depth from the perspectives of feasibility, completeness and security. In specific, we present Responsible Task Automation (ResponsibleTA) as a fundamental framework to facilitate responsible collaboration between LLM-based coordinators and executors for task automation with three empowered capabilities: 1) predicting the feasibility of the commands for executors; 2) verifying the completeness of executors; 3) enhancing the security (e.g., the protection of users' privacy). We further propose and compare two paradigms for implementing the first two capabilities. One is to leverage the generic knowledge of LLMs themselves via prompt engineering while the other is to adopt domain-specific learnable models. Moreover, we introduce a local memory mechanism for achieving the third capability. We evaluate our proposed ResponsibleTA on UI task automation and hope it could bring more attentions to ensuring LLMs more responsible in diverse scenarios. The research project homepage is at https://task-automation-research.github.io/responsible_task_automation.

The principal goal of the TREC Neural Cross-Language Information Retrieval (NeuCLIR) track is to study the impact of neural approaches to cross-language information retrieval. The track has created four collections, large collections of Chinese, Persian, and Russian newswire and a smaller collection of Chinese scientific abstracts. The principal tasks are ranked retrieval of news in one of the three languages, using English topics. Results for a multilingual task, also with English topics but with documents from all three newswire collections, are also reported. New in this second year of the track is a pilot technical documents CLIR task for ranked retrieval of Chinese technical documents using English topics. A total of 220 runs across all tasks were submitted by six participating teams and, as baselines, by track coordinators. Task descriptions and results are presented.

Neuroimage processing tasks like segmentation, reconstruction, and registration are central to the study of neuroscience. Robust deep learning strategies and architectures used to solve these tasks are often similar. Yet, when presented with a new task or a dataset with different visual characteristics, practitioners most often need to train a new model, or fine-tune an existing one. This is a time-consuming process that poses a substantial barrier for the thousands of neuroscientists and clinical researchers who often lack the resources or machine-learning expertise to train deep learning models. In practice, this leads to a lack of adoption of deep learning, and neuroscience tools being dominated by classical frameworks. We introduce Neuralizer, a single model that generalizes to previously unseen neuroimaging tasks and modalities without the need for re-training or fine-tuning. Tasks do not have to be known a priori, and generalization happens in a single forward pass during inference. The model can solve processing tasks across multiple image modalities, acquisition methods, and datasets, and generalize to tasks and modalities it has not been trained on. Our experiments on coronal slices show that when few annotated subjects are available, our multi-task network outperforms task-specific baselines without training on the task.

The use of operating system API calls is a promising task in the detection of PE-type malware in the Windows operating system. This task is officially defined as running malware in an isolated sandbox environment, recording the API calls made with the Windows operating system and sequentially analyzing these calls. Here, we have analyzed 7107 different malicious software belonging to various families such as virus, backdoor, trojan in an isolated sandbox environment and transformed these analysis results into a format where different classification algorithms and methods can be used. First, we'll explain how we got the malware, and then we'll explain how we've got these software bundled into families. Finally, we will describe how to perform malware classification tasks using different computational methods for the researchers who will use the data set we have created.

One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent. To measure progress towards that goal, we argue for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering. Our tasks measure understanding in several ways: whether a system is able to answer questions via chaining facts, simple induction, deduction and many more. The tasks are designed to be prerequisites for any system that aims to be capable of conversing with a human. We believe many existing learning systems can currently not solve them, and hence our aim is to classify these tasks into skill sets, so that researchers can identify (and then rectify) the failings of their systems. We also extend and improve the recently introduced Memory Networks model, and show it is able to solve some, but not all, of the tasks.

We describe the SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials. Although this was a new task, we had a total of 26 submissions across 3 evaluation scenarios. We expect the task and the findings reported in this paper to be relevant for researchers working on understanding scientific content, as well as the broader knowledge base population and information extraction communities.

In populous countries, pending legal cases have been growing exponentially. There is a need for developing NLP-based techniques for processing and automatically understanding legal documents. To promote research in the area of Legal NLP we organized the shared task LegalEval - Understanding Legal Texts at SemEval 2023. LegalEval task has three sub-tasks: Task-A (Rhetorical Roles Labeling) is about automatically structuring legal documents into semantically coherent units, Task-B (Legal Named Entity Recognition) deals with identifying relevant entities in a legal document and Task-C (Court Judgement Prediction with Explanation) explores the possibility of automatically predicting the outcome of a legal case along with providing an explanation for the prediction. In total 26 teams (approx. 100 participants spread across the world) submitted systems paper. In each of the sub-tasks, the proposed systems outperformed the baselines; however, there is a lot of scope for improvement. This paper describes the tasks, and analyzes techniques proposed by various teams.

The CheckThat! lab aims to advance the development of innovative technologies designed to identify and counteract online disinformation and manipulation efforts across various languages and platforms. The first five editions focused on key tasks in the information verification pipeline, including check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, the lab has expanded its scope to address auxiliary tasks that support research and decision-making in verification. In the 2025 edition, the lab revisits core verification tasks while also considering auxiliary challenges. Task 1 focuses on the identification of subjectivity (a follow-up from CheckThat! 2024), Task 2 addresses claim normalization, Task 3 targets fact-checking numerical claims, and Task 4 explores scientific web discourse processing. These tasks present challenging classification and retrieval problems at both the document and span levels, including multilingual settings.

Many natural language processing (NLP) tasks in English or general domains are widely available and are often used to evaluate pre-trained language models. In contrast, there are fewer tasks available for languages other than English and for the financial domain. In particular, tasks in Japanese and the financial domain are limited. We construct two large datasets using materials published by a Japanese central government agency. The datasets provide three Japanese financial NLP tasks, which include a 3-class and 12-class classification for categorizing sentences, as well as a 5-class classification task for sentiment analysis. Our datasets are designed to be comprehensive and up-to-date, leveraging an automatic update framework that ensures the latest task datasets are publicly available anytime.

With the course of progress in the field of medicine, most of the patients lives can be saved. The only thing required is the proper attention at the proper time. Our wearable solution tries to solve this issue by taking the patients vitals and transmitting them to the server for live monitoring using the mobile app along with the patients current location. In case of an emergency, that is if any vitals show any abnormalities, an SMS is sent to the caregiver of the patient with the patients location so that he can reach there on time.

We introduce MURA, a large dataset of musculoskeletal radiographs containing 40,561 images from 14,863 studies, where each study is manually labeled by radiologists as either normal or abnormal. To evaluate models robustly and to get an estimate of radiologist performance, we collect additional labels from six board-certified Stanford radiologists on the test set, consisting of 207 musculoskeletal studies. On this test set, the majority vote of a group of three radiologists serves as gold standard. We train a 169-layer DenseNet baseline model to detect and localize abnormalities. Our model achieves an AUROC of 0.929, with an operating point of 0.815 sensitivity and 0.887 specificity. We compare our model and radiologists on the Cohen's kappa statistic, which expresses the agreement of our model and of each radiologist with the gold standard. Model performance is comparable to the best radiologist performance in detecting abnormalities on finger and wrist studies. However, model performance is lower than best radiologist performance in detecting abnormalities on elbow, forearm, hand, humerus, and shoulder studies. We believe that the task is a good challenge for future research. To encourage advances, we have made our dataset freely available at https://stanfordmlgroup.github.io/competitions/mura .

Although large language models (LLMs) are increasingly capable, these capabilities are unevenly distributed: they excel at formal linguistic tasks, such as producing fluent, grammatical text, but struggle more with functional linguistic tasks like reasoning and consistent fact retrieval. Inspired by neuroscience, recent work suggests that to succeed on both formal and functional linguistic tasks, LLMs should use different mechanisms for each; such localization could either be built-in or emerge spontaneously through training. In this paper, we ask: do current models, with fast-improving functional linguistic abilities, exhibit distinct localization of formal and functional linguistic mechanisms? We answer this by finding and comparing the "circuits", or minimal computational subgraphs, responsible for various formal and functional tasks. Comparing 5 LLMs across 10 distinct tasks, we find that while there is indeed little overlap between circuits for formal and functional tasks, there is also little overlap between formal linguistic tasks, as exists in the human brain. Thus, a single formal linguistic network, unified and distinct from functional task circuits, remains elusive. However, in terms of cross-task faithfulness - the ability of one circuit to solve another's task - we observe a separation between formal and functional mechanisms, suggesting that shared mechanisms between formal tasks may exist.

We present the FinCausal 2020 Shared Task on Causality Detection in Financial Documents and the associated FinCausal dataset, and discuss the participating systems and results. Two sub-tasks are proposed: a binary classification task (Task 1) and a relation extraction task (Task 2). A total of 16 teams submitted runs across the two Tasks and 13 of them contributed with a system description paper. This workshop is associated to the Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), held at The 28th International Conference on Computational Linguistics (COLING'2020), Barcelona, Spain on September 12, 2020.

To deploy language models safely, it is crucial that they abstain from responding to inappropriate requests. Several prior studies test the safety promises of models based on their effectiveness in blocking malicious requests. In this work, we focus on evaluating the underlying techniques that cause models to abstain. We create SELECT, a benchmark derived from a set of benign concepts (e.g., "rivers") from a knowledge graph. Focusing on benign concepts isolates the effect of safety training, and grounding these concepts in a knowledge graph allows us to study the generalization and specificity of abstention techniques. Using SELECT, we benchmark different abstention techniques over six open-weight and closed-source models. We find that the examined techniques indeed cause models to abstain with over 80% abstention rates. However, these techniques are not as effective for descendants of the target concepts, where abstention rates drop by 19%. We also characterize the generalization-specificity trade-offs for different techniques. Overall, no single technique is invariably better than others, and our findings inform practitioners of the various trade-offs involved.

Enterprise networks are growing ever larger with a rapidly expanding attack surface, increasing the volume of security alerts generated from security controls. Security Operations Centre (SOC) analysts triage these alerts to identify malicious activity, but they struggle with alert fatigue due to the overwhelming number of benign alerts. Organisations are turning to managed SOC providers, where the problem is amplified by context switching and limited visibility into business processes. A novel system, named AACT, is introduced that automates SOC workflows by learning from analysts' triage actions on cybersecurity alerts. It accurately predicts triage decisions in real time, allowing benign alerts to be closed automatically and critical ones prioritised. This reduces the SOC queue allowing analysts to focus on the most severe, relevant or ambiguous threats. The system has been trained and evaluated on both real SOC data and an open dataset, obtaining high performance in identifying malicious alerts from benign alerts. Additionally, the system has demonstrated high accuracy in a real SOC environment, reducing alerts shown to analysts by 61% over six months, with a low false negative rate of 1.36% over millions of alerts.

This paper describes a strategy for implementing a robotic system capable of performing General Purpose Service Robot (GPSR) tasks in robocup@home. The GPSR task is that a real robot hears a variety of commands in spoken language and executes a task in a daily life environment. To achieve the task, we integrate foundation models based inference system and a state machine task executable. The foundation models plan the task and detect objects with open vocabulary, and a state machine task executable manages each robot's actions. This system works stable, and we took first place in the RoboCup@home Japan Open 2022's GPSR with 130 points, more than 85 points ahead of the other teams.

Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this primer paper, we propose an actionable guideline to help healthcare professionals more efficiently utilize LLMs in their work, along with a set of best practices. This approach consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and deployment. We start with the discussion of critical considerations in identifying healthcare tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner.