Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
This addresses the need for more traceable and clinically relevant reasoning in medical AI, though it is incremental as it builds on existing chain-of-thought methods.
The paper tackles the problem of improving reasoning accuracy and interpretability in medical visual question answering by introducing Step-CoT, a large-scale dataset with expert-curated, structured multi-step chain-of-thought rationales aligned to clinical workflows, which improved performance in experiments.
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