2 papers
cs.LG2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update
Qing Li, Jiahui Geng, Zongxiong Chen +3
Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large l…
cs.CL2024
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
Derui Zhu, Dingfan Chen, Qing Li +4
Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, whe…