A lightweight hallucination detector that uses sparse autoencoders to identify, explain, and mitigate unfaithful RAG outputs
Guangzhi Xiong
gzxiong
·
AI & ML interests
None yet
Recent Activity
authored a paper 5 days ago
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models submitted a paper 6 days ago
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language ModelsOrganizations
