mlsanityData to 7 Oct 2026

CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation

arXiv 2406.11451 ↗First posted 17 Jun 2024cs.CVcited by 25

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasing attention. Despite recent progress, generating accurate reports remains arduous due to the requirement for precise clinical comprehension and disease diagnosis inference. Furthermore, owing to the limited accessibility of medical data and the imbalanced distribution of diseases, the underrepresentation of rare diseases in training data makes large-scale medical visual language models (LVLMs) prone to hallucinations, such as omissions or fabrications, severely undermining diagnostic performance and further intensifying the challenges for MRG in practice. In this study, to effectively mitigate hallucinations in medical report generation, we propose a chain-of-medical-thought approach (CoMT), which intends to imitate the cognitive process of human doctors by decomposing diagnostic procedures. The radiological features with different importance are structured into fine-grained medical thought chains to enhance the inferential ability during diagnosis, thereby alleviating hallucination problems and enhancing the diagnostic accuracy of MRG. The code and dataset have been released at https://github.com/FRENKIE-CHIANG/CoMT.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 21 of its 32 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

21 of 32 references.

References · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  5. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  6. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  7. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 590
  8. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  9. 2020Generating Radiology Reports via Memory-driven Transformercited by 363
  10. 2023Improving CLIP Training with Language Rewritescited by 216
  11. 2017On the Automatic Generation of Medical Imaging Reportscited by 215
  12. 2021Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generationcited by 160
9 more
  1. 2020When Radiology Report Generation Meets Knowledge Graphcited by 144
  2. 2023PromptMRG: Diagnosis-Driven Prompts for Medical Report Generationcited by 92
  3. 2021Contrastive Attention for Automatic Chest X-ray Report Generationcited by 71
  4. 2023Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewritescited by 61
  5. 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Modelscited by 57
  6. 2023Mitigating Hallucination in Visual Language Models with Visual Supervisioncited by 49
  7. 2024Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Braincited by 32
  8. 2017Recurrent Topic-Transition GAN for Visual Paragraph Generationcited by 25
  9. 2024MISS: A Generative Pretraining and Finetuning Approach for Med-VQAcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 8.

25 papers.

Sort:

By area:

  1. 2025Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoningcited by 19
  2. 2025The Rise of Small Language Models in Healthcare: A Comprehensive Surveycited by 18
  3. 2025Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Modelscited by 17
  4. 2025Vision Language Models in Medicinecited by 12
  5. 2026MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolutioncited by 12
  6. 2025MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Modelscited by 10
  7. 2025Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Modelscited by 9
  8. 2025DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understandingcited by 7
  9. 2025MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoningcited by 6
  10. 2025TECP: Token-Entropy Conformal Prediction for LLMscited by 5
  11. 2025Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source Large Language Modelscited by 4
  12. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generationcited by 3
13 more
  1. 2025Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuningcited by 3
  2. 2025SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image Comprehensioncited by 3
  3. 2026MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialoguecited by 2
  4. 2025Scalable Medication Extraction and Discontinuation Identification from Electronic Health Records Using Large Language Modelscited by 1
  5. 2025COPO: Consistency-Aware Policy Optimizationcited by 1
  6. 2025Enhancing Medical Large Vision-Language Models via Alignment Distillationcited by 1
  7. 2026ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Modelscited by 1
  8. 2026Evaluating the Search Agent in a Parallel Worldcited by 1
  9. 2026Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generationcited by 1
  10. 2026MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rayscited by 1
  11. 2025SPADE: A Large Language Model Framework for Soil Moisture Pattern Recognition and Anomaly Detection in Precision Agriculturecited by 0
  12. 2026LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answeringcited by 0
  13. 2026DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Makingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Hallucination Mitigating for Medical Report Generation
  2. 2025Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation
  3. 2024RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
  4. 2025CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding
  5. 2024ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
  6. 2026Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering
  7. 2026HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation
  8. 2024MedHallBench: A New Benchmark for Assessing Hallucination in Medical Large Language Models