mlsanityData to 7 Oct 2026

Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning

arXiv 2509.06409 ↗First posted 8 Sep 2025cs.AIcited by 1

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

This study presents DiagCoT, a multi-stage framework that applies supervised fine-tuning to general-purpose vision-language models (VLMs) to emulate radiologists' stepwise diagnostic reasoning using only free-text reports. DiagCoT combines contrastive image-report tuning for domain alignment, chain-of-thought supervision to capture inferential logic, and reinforcement tuning with clinical reward signals to enhance factual accuracy and fluency. On the MIMIC-CXR benchmark, DiagCoT improved zero-shot disease classification AUC from 0.52 to 0.76 (absolute gain of 0.24), pathology grounding mIoU from 0.08 to 0.31 (absolute gain of 0.23), and report generation BLEU from 0.11 to 0.33 (absolute gain of 0.22). It outperformed state-of-the-art models including LLaVA-Med and CXR-LLAVA on long-tailed diseases and external datasets. By converting unstructured clinical narratives into structured supervision, DiagCoT offers a scalable approach for developing interpretable and diagnostically competent AI systems for radiology.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 11 of its 42 references that are in the map. First posted on arXiv 8 Sep 2025.

Builds on

11 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification29 Apr
  2. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models18 Mar

Other references · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Deep reinforcement learning from human preferencescited by 3,846
  3. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  4. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
  5. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 653
  6. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  7. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 501
  8. 2024A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretationcited by 79
  9. 2025MoColl: Agent-Based Specific and General Model Collaboration for Image Captioningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026UR2-MLLM: Uncertainty-aware Revisit Reasoning in Multimodal Large Language Models for Radiology Report Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Visual Language Model for Chest X-Ray Analysis
  2. 2026Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
  3. 2026Enhancing Visual Reasoning in Chest X-Ray Report Generation Using Reinforcement Learning
  4. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
  5. 2025Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning
  6. 2025Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning
  7. 2025RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation
  8. 2026Evaluating GPT-5 as a Multimodal Clinical Reasoner: A Landscape Commentary