Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
Paper • 2501.02654 • Published
Yang Wang
yangwang825
AI & ML interests
Natural Language Processing, Psychological LLMs, Multi-modality Learning, Knowledge/Reasoning Boundary.
Recent Activity
updated a dataset about 6 hours ago
yangwang825/91e3d56b0a-part012 updated a dataset about 6 hours ago
yangwang825/91e3d56b0a-part013 updated a dataset about 7 hours ago
yangwang825/91e3d56b0a-part011Organizations
authored a
paper 6 months ago
authored 4
papers 7 months ago
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth
Paper • 2509.03867 • Published • 213
Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
Paper • 2507.21750 • Published • 1
Audio Contrastive based Fine-tuning
Paper • 2309.11895 • Published • 1
From Facts to Insights: A Study on the Generation and Evaluation of Analytical Reports for Deciphering Earnings Calls
Paper • 2410.01039 • Published