构建可追溯的多步医学视觉推理数据集，提升诊断准确性与模型可解释性。
Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
- 基于临床诊断流程构建结构化多步推理链，引导模型按规范路径思考。
- 在超过1万例真实病例上验证，显著提升医学图像问答准确率。
- 适合医疗AI研究者、临床辅助系统开发者使用，推动可信AI落地。
思维链（CoT）推理已推动医学视觉问答（VQA）发展，但现有大多数思维链为自由形式，未能捕捉临床医生实际遵循的结构化推理过程。本文提出：可追溯的多步推理监督能否提升医学VQA的推理准确性和可解释性？为此，我们构建了Step-CoT——一个大规模医学推理数据集，包含专家标注的、与临床诊断流程对齐的结构化多步思维链，隐式将模型推理锚定在放射学证据上。Step-CoT涵盖超过10,000个真实临床案例和70,000组VQA对，围绕诊断流程组织，提供有监督的中间步骤，引导模型遵循有效推理路径。为高效学习此数据，我们进一步提出一种教师-学生框架，结合动态图结构聚焦机制，优先关注具有诊断意义的步骤并过滤无关上下文。实验表明，使用Step-CoT能显著提升推理准确率与可解释性。基准代码：github.com/hahaha111111/Step-CoT；数据集卡片：huggingface.co/datasets/fl-15o/Step-CoT。
原文摘要 · Abstract (English)
Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning process clinicians actually follow. This work asks: Can traceable, multi-step reasoning supervision improve reasoning accuracy and the interpretability of Medical VQA? To this end, we introduce Step-CoT, a large-scale medical reasoning dataset with expert-curated, structured multi-step CoT aligned to clinical diagnostic workflows, implicitly grounding the model's reasoning in radiographic evidence. Step-CoT comprises more than 10K real clinical cases and 70K VQA pairs organized around diagnostic workflows, providing supervised intermediate steps that guide models to follow valid reasoning trajectories. To effectively learn from Step-CoT, we further introduce a teacher-student framework with a dynamic graph-structured focusing mechanism that prioritizes diagnostically informative steps while filtering out less relevant contexts. Our experiments show that using Step-CoT can improve reasoning accuracy and interpretability. Benchmark: github.com/hahaha111111/Step-CoT. Dataset Card: huggingface.co/datasets/fl-15o/Step-CoT
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。