论视觉思维的可信度：测量与增强
On the Faithfulness of Visual Thinking: Measurement and Enhancement
AI总结：
针对多模态思维链中视觉信息不可信的问题，提出测量方法并引入SCCM学习策略，通过生成充分且最小的视觉组件，在无需标注下提升视觉可信度。
摘要：
近年来，大型视觉语言模型（LVLMs）在强化微调（RFT）后能够生成视觉-文本多模态思维链（MCoT）轨迹。然而，我们观察到MCoT中包含的视觉信息往往不准确，尽管仍能产生正确答案，这表明MCoT推理过程缺乏可信度。我们将这种不可信归因于RFT中的强化学习奖励，该奖励仅激励交错视觉-文本线索的格式，即鼓励模型将视觉信息纳入其文本推理步骤，而不考虑视觉信息的正确性。在本文中，我们首先通过测量当视觉和文本思维受到干预时预测的变化来探究MCoT的可信度。令人惊讶的是，在视觉干预下模型的预测几乎保持不变，但在文本干预下变化显著，表明视觉证据在很大程度上被忽略。为了进一步分析视觉信息，我们引入了一种基于LVLM的自动化评估指标，从可靠性和充分性两个角度量化视觉线索的可信度。我们的评估显示，当前MCoT轨迹中的视觉信息既不可靠也不充分。为了解决这个问题，我们提出了一种新颖的MCoT学习策略，称为充分组件因果模型（SCCM）学习。该方法鼓励MCoT生成充分且最小的视觉组件，这些组件能够独立地导致正确答案。我们注意到，所提出的SCCM无需标注，并且以即插即用的方式与各种用于MCoT的RFT兼容。实证结果表明，SCCM在一系列细粒度感知和推理基准上持续提高了视觉可信度。代码可在https://github.com/EugeneLiu01/Faithful_Thinking_with_Image获取。
英文摘要：
Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the visual information incorporated in MCoT is often inaccurate, though still yield correct answers, indicating a lack of faithfulness in the MCoT reasoning process. We attribute this unfaithfulness to the RL reward in RFT, which solely incentivizes the format of interleaved vision-text cues, ie, it encourages the model to incorporate visual information into its text reasoning steps without considering the correctness of the visual information. In this paper, we first probe the faithfulness of MCoT by measuring how much the prediction changes when its visual and textual thoughts are intervened. Surprisingly, the model's predictions remain nearly unchanged under visual intervention but change significantly under textual intervention, indicating that the visual evidence is largely ignored. To further analyze visual information, we introduce an automated LVLM-based evaluation metric that quantifies the faithfulness of visual cues from two perspectives: reliability and sufficiency. Our evaluation reveals that the visual information in current MCoT traces is simultaneously unreliable and insufficient. To address this issue, we propose a novel MCoT learning strategy termed Sufficient-Component Cause Model (SCCM) learning. This approach encourages the MCoT to generate sufficient yet minimal visual components that are independently capable of leading to correct answers. We note that the proposed SCCM is annotation-free and compatible with various RFT for MCoT in a plug-and-play manner. Empirical results demonstrate that SCCM consistently improves the visual faithfulness across a suite of fine-grained perception and reasoning benchmarks. Code is available at https://github.com/EugeneLiu01/Faithful_Thinking_with_Image.
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。
