HaloProbe: 基于贝叶斯的方法检测和缓解视觉-语言模型中的物体幻觉
HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
AI总结：
本文提出HaloProbe框架，通过结合外部描述统计和内部解码信号，有效检测和缓解视觉-语言模型中的物体幻觉，实验表明其比现有干预方法更有效且保持了模型的实用性。
摘要：
大型视觉-语言模型在图像描述中可能产生物体幻觉，凸显了有效检测和缓解策略的必要性。先前工作通常依赖模型对视觉标记的注意力权重作为检测信号。我们发现，基于粗粒度注意力分析不可靠，因为存在隐藏的混杂因素，特别是描述中的标记位置和物体重复。这导致了辛普森悖论：当统计数据汇总时，注意力趋势会反转或消失。基于此观察，我们引入HaloProbe，一种贝叶斯框架，通过分解外部描述统计和内部解码信号来估计标记级别的幻觉概率。HaloProbe通过平衡训练来隔离内部证据，并将其与学习到的外部特征先验相结合，以恢复真实的后验。尽管基于干预的缓解方法通常通过修改模型内部而降级实用性和流畅性，我们使用HaloProbe作为外部评分信号进行非侵入式缓解。我们的实验表明，HaloProbe引导的解码在缓解幻觉方面比最先进的干预方法更有效，同时保持了模型的实用性。
英文摘要：
Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation strategies. Prior work commonly relies on the model's attention weights on visual tokens as a detection signal. We reveal that coarse-grained attention-based analysis is unreliable due to hidden confounders, specifically token position and object repetition in a description. This leads to Simpson's paradox: the attention trends reverse or disappear when statistics are aggregated. Based on this observation, we introduce HaloProbe, a Bayesian framework that factorizes external description statistics and internal decoding signals to estimate token-level hallucination probabilities. HaloProbe uses balanced training to isolate internal evidence and combines it with a learned prior over external features to recover the true posterior. While intervention-based mitigation methods often degrade utility or fluency by modifying models' internals, we use HaloProbe as an external scoring signal for non-invasive mitigation. Our experiments show that HaloProbe-guided decoding reduces hallucinations more effectively than state-of-the-art intervention-based methods while preserving utility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
