mlsanityData to 14 Oct 2026

MedCoT: Medical Chain of Thought via Hierarchical Expert

arXiv 2412.13736 ↗First posted 18 Dec 2024cs.CVcited by 46

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Artificial intelligence has advanced in Medical Visual Question Answering (Med-VQA), but prevalent research tends to focus on the accuracy of the answers, often overlooking the reasoning paths and interpretability, which are crucial in clinical settings. Besides, current Med-VQA algorithms, typically reliant on singular models, lack the robustness needed for real-world medical diagnostics which usually require collaborative expert evaluation. To address these shortcomings, this paper presents MedCoT, a novel hierarchical expert verification reasoning chain method designed to enhance interpretability and accuracy in biomedical imaging inquiries. MedCoT is predicated on two principles: The necessity for explicit reasoning paths in Med-VQA and the requirement for multi-expert review to formulate accurate conclusions. The methodology involves an Initial Specialist proposing diagnostic rationales, followed by a Follow-up Specialist who validates these rationales, and finally, a consensus is reached through a vote among a sparse Mixture of Experts within the locally deployed Diagnostic Specialist, which then provides the definitive diagnosis. Experimental evaluations on four standard Med-VQA datasets demonstrate that MedCoT surpasses existing state-of-the-art approaches, providing significant improvements in performance and interpretability.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 28 of its 38 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

28 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale18 Apr

Other references · 27

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  6. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  7. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  8. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  9. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 781
  10. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
  11. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  12. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
15 more
  1. 2018Bilinear Attention Networkscited by 280
  2. 2022A Review of Sparse Expert Models in Deep Learningcited by 148
  3. 2023DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Modelscited by 128
  4. 2022CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailmentcited by 113
  5. 2022Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Trainingcited by 88
  6. 2021Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?cited by 85
  7. 2019Overcoming Data Limitation in Medical Visual Question Answeringcited by 71
  8. 2021MMBERT: Multimodal BERT Pretraining for Improved Medical VQAcited by 68
  9. 2022All You May Need for VQA are Image Captionscited by 65
  10. 2022Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledgecited by 51
  11. 2022CLIP-TD: CLIP Targeted Distillation for Vision-Language Taskscited by 32
  12. 2023A ChatGPT Aided Explainable Framework for Zero-Shot Medical Image Diagnosiscited by 31
  13. 2021Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answeringcited by 26
  14. 2020WeaQA: Weak Supervision via Captions for Visual Question Answeringcited by 25
  15. 2023Scalable Geometric Fracture Assembly via Co-creation Space among Assemblerscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 36; 2026: 10.

46 papers.

Sort:

By area:

  1. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 182
  2. 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworkscited by 40
  3. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  4. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  5. 20253D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Taskscited by 26
  6. 2025OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understandingcited by 17
  7. 2025Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Supportcited by 16
  8. 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Searchcited by 16
  9. 2025Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospectscited by 12
  10. 2025A Survey of Scaling in Large Language Model Reasoningcited by 10
  11. 2025Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learningcited by 10
  12. 2025OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoningcited by 10
34 more
  1. 2025RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraintscited by 9
  2. 2025UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localizationcited by 9
  3. 2025AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretationcited by 8
  4. 2025Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learningcited by 8
  5. 2025MedEthicsQA: A Comprehensive Question Answering Benchmark for Medical Ethics Evaluation of LLMscited by 8
  6. 2025Med-GLIP: Advancing Medical Language-Image Pre-training with Large-scale Grounded Datasetcited by 7
  7. 2025Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Modelscited by 6
  8. 2025CATCH: A Modular Cross-domain Adaptive Template with Hookcited by 6
  9. 2025CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decodingcited by 4
  10. 2026Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicinecited by 4
  11. 2026Medical thinking with multiple imagescited by 4
  12. 2025CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimizationcited by 3
  13. 2025Trustworthy and Fair SkinGPT-R1 for Democratizing Dermatological Reasoning across Diverse Ethnicitiescited by 3
  14. 2026MM-NeuroOnco: A Multimodal Benchmark and Instruction Dataset for MRI-Based Brain Tumor Diagnosiscited by 3
  15. 2026Can Large Language Models Self-Correct in Medical Question Answering? An Exploratory Studycited by 3
  16. 2025TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verificationcited by 2
  17. 2025DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaborationcited by 2
  18. 2025Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Makingcited by 2
  19. 2025Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQAcited by 2
  20. 2025Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learningcited by 2
  21. 2025Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narrativescited by 2
  22. 2025Foundation Models in Biomedical Imaging: Turning Hype into Realitycited by 2
  23. 2026Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answeringcited by 2
  24. 2025Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusioncited by 1
  25. 2025HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Modelscited by 1
  26. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  27. 2026MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultationcited by 1
  28. 2026Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoningcited by 1
  29. 2025Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoningcited by 0
  30. 2025Modest-Align: Data-Efficient Alignment for Vision-Language Modelscited by 0
  31. 2025MedCalc-Eval and MedCalc-Env: Advancing Medical Calculation Capabilities of Large Language Modelscited by 0
  32. 2026Surrogate modeling for interpreting black-box LLMs in medical predictionscited by 0
  33. 2026Thinking Like a Botanist: Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquirycited by 0
  34. 2026Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering
  2. 2023Visual Question Answering in the Medical Domain
  3. 2025MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models
  4. 2024MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models
  5. 2025GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning
  6. 2026LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
  7. 2025S-Chain: Structured Visual Chain-of-Thought For Medicine
  8. 2026MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence