理解并缓解多模态思维链模型中的幻觉
Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
针对多模态思维链模型在复杂视觉推理中的幻觉问题，提出定位发散思维步骤并在解码阶段干预的方法，可直接用于提升视觉推理链的可靠性，且能与其他幻觉缓解策略叠加。
原文依据 fabricated texts are primarily generated in associative reasoning steps, which we term divergent thinking
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态思维链（MCoT）模型在复杂视觉推理任务中展现出令人印象深刻的能力。然而，近期研究揭示，由于生成过程中视觉注意力减弱，这些模型存在严重的幻觉问题。不过，视觉注意力衰减在大规模视觉语言模型（LVLM）中是一个已被充分研究的问题。考虑到MCoT模型与传统LVLM在推理过程上的根本差异，我们提出一个基本问题：MCoT模型是否存在独特的幻觉成因？为回答这一问题，我们系统性地研究了MCoT模型的幻觉模式，发现虚构文本主要产生于联想推理步骤，我们将其称为发散思维。基于这些发现，我们引入一种简单而有效的策略，能够有效定位发散思维步骤并在解码过程中进行干预以缓解幻觉。大量实验表明，我们的方法大幅优于现有方法。更重要的是，我们提出的方法可以方便地与其他幻觉缓解方法集成，并进一步提升其性能。代码已公开于 https://github.com/ASGO-MM/MCoT-hallucination。
英文原文摘要 1293 字符
Multimodal Chain-of-Thought (MCoT) models have demonstrated impressive capability in complex visual reasoning tasks. Unfortunately, recent studies reveal that they suffer from severe hallucination problems due to diminished visual attention during the generation process.However, visual attention decay is a well-studied problem in Large Vision-Language Models (LVLMs). Considering the fundamental differences in reasoning processes between MCoT models and traditional LVLMs, we raise a basic question: Whether MCoT models have unique causes of hallucinations? To answer this question, we systematically investigate the hallucination patterns of MCoT models and find that fabricated texts are primarily generated in associative reasoning steps, which we term divergent thinking. Leveraging these insights, we introduce a simple yet effective strategy that can effectively localize divergent thinking steps and intervene in the decoding process to mitigate hallucinations. Extensive experiments show that our method outperforms existing methods by a large margin. More importantly, our proposed method can be conveniently integrated with other hallucination mitigation methods and further boost their performance. The code is publicly available at https://github.com/ASGO-MM/MCoT-hallucination.