作者位次 #3/4ACL 2026Poster· Natural Language Processing
Latent Attention Denoising: A Training-Free Energy-Based Framework for Mitigating Hallucinations in Vision-Language Models
Zhiwen Luo · Siyu Jiang · Weilong Jiang · Kun He
摘要
Visual hallucination remains a major obstacle to the reliability of Large Vision-Language Models (LVLMs). We argue that this issue originates from a fundamental statistical misspecification: the conventional softmax attention implicitly assumes i.i.d. noise, yet real LVLM attention patterns exhib...