Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering

About

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

Lin Fan, Yafei Ou, Zhipeng Deng, Pengyu Dai, Hou Chongxian, Jiale Yan, Yaqian Li, Kaiwen Long, Xun Gong, Masayuki Ikebe, Yefeng Zheng• 2026

Related benchmarks

TaskDatasetResultRank
Medical DiagnosisStep-CoT (test)
Accuracy78.3
10
DetectionClinical Expert Evaluation set (N=200)
Accuracy88.5
6
Anatomical locationClinical Expert Evaluation set (N=200)
Accuracy72.8
3
DiagnosisClinical Expert Evaluation set (N=200)
Accuracy79.8
3
Lesion distributionClinical Expert Evaluation set (N=200)
Accuracy78.4
3
Morphologic featureClinical Expert Evaluation set (N=200)
Accuracy84.8
3
Stepwise Medical ReasoningStep-CoT 200 cases sample (test)
Detection Score88.5
3
Secondary effects/associated signsClinical Expert Evaluation set (N=200)
Accuracy75.2
3
Showing 8 of 8 rows

Other info

Follow for update