Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
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
Record details
Published: 14 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Healthcare
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Formal Abductive Explanations for Navigating Mental Health Help-Seeking and Diversity in Tech Workplaces
arXiv · 14 March 2026
Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
arXiv · 15 March 2026
Emulating Clinician Cognition via Self-Evolving Deep Clinical Research
arXiv · 11 March 2026
Domain-Adaptive Health Indicator Learning with Degradation-Stage Synchronized Sampling and Cross-Domain Autoencoder
arXiv · 11 March 2026
Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment
arXiv · 11 March 2026
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
arXiv · 17 March 2026
How to cite this record
ethics.ai (14 March 2026), “Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering,” evidence record 7247, https://ethics.ai/record/7247 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.