VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering 事件

VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering arXiv:2605.20772v2 Announce Type: replace Abstract: While medical Multimodal Large Language Models (MLLMs) have shown promise in assisting diagnosis, they still frequently generate hallucinated responses that appear linguistically plausible but lack visual evidence. Such hallucinations pose risks to clinical decision-making and necessitate effective detection. Existing introspective detection methods p