医学视觉问答中，思维链反而拖后腿，因为细节线索易误导模型。
Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
- 用区域提示和优质文本引导增强视觉定位，提升模型理解力。
- 在多个医疗数据集上，新方法使思维链准确率反超直接回答。
- 适合做临床医疗视觉模型的开发者，尤其关注模型可信度者。
大型视觉语言模型（VLMs）在通用领域常受益于思维链（CoT）提示，但在医疗视觉语言任务中的效果尚未充分探索。我们发现一种反直觉现象：在医学视觉问答任务中，无论是通用模型还是医疗专用模型，思维链（CoT）的表现普遍低于直接回答（DirA）。我们将其归因于「医学感知瓶颈」：细微的领域特定线索会削弱视觉定位，而思维链可能放大早期感知不确定性而非纠正它。为验证此假设，我们提出两种无需训练、仅在推理时使用的定位干预方法：(i) 通过感兴趣区域提示实现感知锚定；(ii) 通过高质量文本指导实现描述锚定。在多个基准测试和模型族中，这些干预显著提升准确率，缓解了思维链的性能下降，并在若干场景下逆转了CoT与DirA的性能倒置。研究结果表明，可靠的临床视觉语言模型需要更强的视觉定位与跨模态对齐能力，而不仅仅是扩展文本驱动的推理链。代码已开源。
原文摘要 · Abstract (English)
Large vision-language models (VLMs) often benefit from chain-of-thought (CoT) prompting in general domains, yet its efficacy in medical vision-language tasks remains underexplored. We report a counter-intuitive trend: on medical visual question answering, CoT frequently underperforms direct answering (DirA) across general-purpose and medical-specific models. We attribute this to a \emph{medical perception bottleneck}: subtle, domain-specific cues can weaken visual grounding, and CoT may compound early perceptual uncertainty rather than correct it. To probe this hypothesis, we introduce two training-free, inference-time grounding interventions: (i) \emph{perception anchoring} via region-of-interest cues and (ii) \emph{description grounding} via high-quality textual guidance. Across multiple benchmarks and model families, these interventions improve accuracy, mitigate CoT degradation, and in several settings reverse the CoT--DirA inversion. Our findings suggest that reliable clinical VLMs require robust visual grounding and cross-modal alignment, beyond extending text-driven reasoning chains. Code is available \href{https://github.com/TianYin123/Better_Eyes_Better_Thoughts}{here}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。