作者位次 #3/6ACL 2026Poster· Natural Language Processing
D i VE : Decoupling Intra-layer Visual Evidence for Mitigating Hallucinations in Large Vision-Language Models
Xinwei Li · Li Lin · Hui Jiao · Li Yao · Tien-Tsin Wong · Hanqian Wu
摘要
Recent Large Vision-Language Models (LVLMs) have achieved significant progress yet frequently suffer from visual hallucinations, often stemming from an over-reliance on language priors rather than visual evidence. Existing decoding-based approaches often rely on input perturbations to weaken lang...