mlsanityData to 14 Oct 2026

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

arXiv 2509.23379 ↗First posted 27 Sep 2025cs.CL cs.AI cs.CVcited by 4

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Multimodal large language models (MLLMs) have recently achieved remarkable progress in radiology by integrating visual perception with natural language understanding. However, they often generate clinically unsupported descriptions, known as medical hallucinations, which pose serious risks in medical applications that demand accuracy and image-grounded outputs. Through empirical analysis, we find that prompt-induced hallucinations remain prevalent in radiology MLLMs, largely due to over-sensitivity to clinical sections. To address this, we introduce Clinical Contrastive Decoding (CCD), a training-free and retrieval-free inference framework that integrates structured clinical signals from task-specific radiology expert models. CCD introduces a dual-stage contrastive mechanism to refine token-level logits during generation, thereby enhancing clinical fidelity without modifying the base MLLM. Experiments on three datasets and multiple models demonstrate that CCD consistently improves overall performance on radiology report generation (RRG). On the MIMIC-CXR dataset, it yields up to a 17% improvement in RadGraph-F1 when applied to state-of-the-art RRG models. Our approach provides a lightweight and generalisable solution for mitigating medical hallucinations, effectively bridging expert models and MLLMs in radiology.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 62 of its 101 references that are in the map. First posted on arXiv 27 Sep 2025.

Builds on

62 of 101 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding22 May
  2. 2025The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering5 Feb
  3. 2024Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens23 Nov
  4. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering21 Oct
  5. 2024Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding17 Oct
  6. 2024MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation15 Oct
  7. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs31 Jul
  8. 2024MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context3 Jul
  9. 2024Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention18 Jun
  10. 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Models14 Jun
  11. 2024Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs24 May
  12. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding27 Mar
5 more
  1. 2024Multi-Modal Hallucination Control by Visual Information Grounding20 Mar
  2. 2024Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance13 Feb
  3. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  4. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  5. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov

Other references · 45

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  7. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  8. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  9. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  10. 2023A Survey on Multimodal Large Language Modelscited by 909
  11. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  12. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 609
33 more
  1. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 597
  2. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  3. 2025MedGemma Technical Reportcited by 436
  4. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
  5. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  6. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 230
  7. 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMscited by 176
  8. 2018TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rayscited by 139
  9. 2019Clinically Accurate Chest X-Ray Report Generationcited by 139
  10. 2024Exploring scalable medical image encoders beyond text supervisioncited by 132
  11. 2021TorchXRayVision: A library of chest X-ray datasets and modelscited by 131
  12. 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 128
  13. 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 109
  14. 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 106
  15. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 100
  16. 2025Medical Hallucinations in Foundation Models and Their Impact on Healthcarecited by 93
  17. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 85
  18. 2025A Survey of LLM-based Agents in Medicine: How far are we from Baymax?cited by 85
  19. 2022Improving the Factual Correctness of Radiology Report Generation with Semantic Rewardscited by 83
  20. 2023Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosiscited by 77
  21. 2018Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classificationcited by 57
  22. 2024A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Taskscited by 57
  23. 2024Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluationcited by 51
  24. 2025DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understandingcited by 49
  25. 2024MedCoT: Medical Chain of Thought via Hierarchical Expertcited by 46
  26. 2024Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiologycited by 45
  27. 2024Libra: Leveraging Temporal Images for Biomedical Radiology Analysiscited by 29
  28. 2024A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Taskscited by 27
  29. 2025RadEval: A framework for radiology text evaluationcited by 22
  30. 2024Hallucination Benchmark in Medical Visual Question Answeringcited by 18
  31. 2023Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learningcited by 17
  32. 2025RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injectioncited by 13
  33. 2024Direct Preference Optimization for Suppressing Hallucinated Prior Exams in Radiology Report Generationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generationcited by 3
  2. 2026CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Modelscited by 1
  3. 2026CCS: Clinical Consensus Selection for Radiology Report Generationcited by 0
  4. 2026SelfCue: Making a 3D CT Report Generator Say What It Already Knowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding
  2. 2026HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation
  3. 2026Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering
  4. 2024RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
  5. 2025Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
  6. 2025Process Reward Models for Sentence-Level Verification of LVLM Radiology Reports
  7. 2024ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
  8. 2025Reducing Hallucinations of Medical Multimodal Large Language Models with Visual Retrieval-Augmented Generation