Ruizhe Li

The paper introduces a new security benchmark and framework to defend LLM agents against 'cognitive poisoning,' where malicious tools build trust through benign feedback before executing a harmful final action.

This paper systematically evaluates how LLMs uncritically adapt to potentially dangerous user prompts related to eating disorders, finding that specific linguistic cues significantly increase the likelihood of unsafe responses.

This paper examines how fine-tuning large audio-language models affects the semantics, decoder accessibility, and temporal output alignment of native audio-token states using temporal audio grounding.