Chain-of-Thought reasoning is widely used to improve the interpretability of multimodal large language models (MLLMs), yet the faithfulness of the generated reasoning traces remains unclear. Prior work has mainly focused on perceptual hallucinations, leaving reasoning level unfaithfulness underexplored. To isolate faithfulness from linguistic priors, we introduce SPD-Faith Bench, a diagnostic benchmark based on fine-grained image difference reasoning that enforces explicit visual comparison. Evaluations on state-of-the-art MLLMs reveal two systematic failure modes, perceptual blindness and perception-reasoning dissociation. We trace these failures to decaying visual attention and representation shifts in the residual stream. Guided by this analysis, we propose SAGE, a train-free visual evidence-calibrated framework that improves visual routing and aligns reasoning with perception. Our results highlight the importance of explicitly evaluating faithfulness beyond response correctness. Our benchmark and codes are available at this https URL.
SPD-Faith Bench：诊断与提升多模态大语言模型思维链推理的忠实性 / SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models
这篇论文提出了一个名为SPD-Faith Bench的诊断基准，用于发现多模态大模型在思维链推理中存在的‘感知盲区’和‘感知-推理脱节’两大不忠实问题，并通过一种无需训练的可视化证据校准框架SAGE来提升推理的可靠性。
源自 arXiv: 2602.07833
