S-Chain：面向医学的结构化视觉思维链

摘要

医疗视觉语言模型（V-LM）的可靠推理不仅需要精准预测，更要求文本推理与视觉证据间保持透明对齐。尽管思维链（CoT）提示在医疗视觉问答（VQA）中展现出潜力，但尚无大规模专家级数据集能提供具备精确视觉定位的渐进式推理。我们推出首个大规模专家标注数据集S-Chain，包含12,000张带边界框的医学图像及结构化视觉CoT（SV-CoT），显式关联视觉区域与推理步骤。该数据集进一步支持16种语言，总计超70万VQA问答对，具备广泛的多语言适用性。基于S-Chain，我们对前沿医疗V-LM（ExGra-Med、LLaVA-Med）及通用V-LM（Qwen2.5-VL、InternVL2.5）进行基准测试，发现SV-CoT监督能显著提升模型可解释性、定位保真度与鲁棒性。除基准测试外，我们还探究其与检索增强生成的协同效应，揭示自回归推理过程中领域知识与视觉定位的交互机制。最后，我们提出一种强化视觉证据与推理对齐的新机制，同步提升可靠性及效率。S-Chain为 grounded 医疗推理树立新基准，为构建更可信、可解释的医疗V-LM开辟道路。

English

Faithful reasoning in medical vision-language models (VLMs) requires not only accurate predictions but also transparent alignment between textual rationales and visual evidence. While Chain-of-Thought (CoT) prompting has shown promise in medical visual question answering (VQA), no large-scale expert-level dataset has captured stepwise reasoning with precise visual grounding. We introduce S-Chain, the first large-scale dataset of 12,000 expert-annotated medical images with bounding boxes and structured visual CoT (SV-CoT), explicitly linking visual regions to reasoning steps. The dataset further supports 16 languages, totaling over 700k VQA pairs for broad multilingual applicability. Using S-Chain, we benchmark state-of-the-art medical VLMs (ExGra-Med, LLaVA-Med) and general-purpose VLMs (Qwen2.5-VL, InternVL2.5), showing that SV-CoT supervision significantly improves interpretability, grounding fidelity, and robustness. Beyond benchmarking, we study its synergy with retrieval-augmented generation, revealing how domain knowledge and visual grounding interact during autoregressive reasoning. Finally, we propose a new mechanism that strengthens the alignment between visual evidence and reasoning, improving both reliability and efficiency. S-Chain establishes a new benchmark for grounded medical reasoning and paves the way toward more trustworthy and explainable medical VLMs.

S-Chain：面向医学的结构化视觉思维链

S-Chain: Structured Visual Chain-of-Thought For Medicine

摘要

Support