4 papers
Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
Wenbo Pan, Zhichao Liu, Xianlong Wang +2
Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as modern LLMs increasingly rely on ext…
Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Wenbo Pan, Jie Xu, Qiguang Chen +5
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, w…
WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
Zhichao Liu, Wenbo Pan, Haining Yu +3
Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process p…
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
Wenbo Pan, Zhichao Liu, Qiguang Chen +3
Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety beh…