Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912966092259328 |
|---|---|
| author | Fan, Lin Ou, Yafei Deng, Zhipeng Dai, Pengyu Chongxian, Hou Yan, Jiale Li, Yaqian Long, Kaiwen Gong, Xun Ikebe, Masayuki Zheng, Yefeng |
| author_facet | Fan, Lin Ou, Yafei Deng, Zhipeng Dai, Pengyu Chongxian, Hou Yan, Jiale Li, Yaqian Long, Kaiwen Gong, Xun Ikebe, Masayuki Zheng, Yefeng |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13878 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering Fan, Lin Ou, Yafei Deng, Zhipeng Dai, Pengyu Chongxian, Hou Yan, Jiale Li, Yaqian Long, Kaiwen Gong, Xun Ikebe, Masayuki Zheng, Yefeng Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language I.2.10; I.2.7; I.2.1; J.3 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 |
| title | Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language I.2.10; I.2.7; I.2.1; J.3 |
| url | https://arxiv.org/abs/2603.13878 |