Elamur Research⌕
☰
home / papers / 2026 / CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

Paper · 2026 · Xi Zhang, Zaiqiao Meng, Jake Lever et al.

Summary

Radiology multimodal LLMs often write findings that the image does not support. The authors call these medical hallucinations. In an empirical study with LLaVA-Med v1.5 on MIMIC-CXR report generation, they add clinical sections (indication, technique, comparison, history) to the prompt. Most lexical and clinical scores get worse. This suggests the models react too strongly to textual context that may be irrelevant or counterfactual.

Their fix is Clinical Contrastive Decoding (CCD), which works only at inference time and needs no training or retrieval. A task-specific radiology expert model, such as a symptom classifier, outputs structured labels and their probabilities. CCD uses these in two contrastive stages that adjust token logits while the report is generated. The labels are written into the prompt as descriptive hints, and the confidence scores perturb decoding. The base MLLM stays unchanged.

Across three datasets and several models, CCD improves radiology report generation and also helps VQA accuracy. On MIMIC-CXR, RadGraph-F1 rises by up to 17%. CCD is a lightweight, privacy-friendly way to combine expert models with generative MLLMs.

Key points

  • The pilot study shows that prompt-induced hallucinations persist even when real clinical sections from MIMIC-CXR are used. The baseline is LLaVA-Med v1.5 with greedy decoding.
  • CCD has two stages:
    • Symptom-grounded decoding (SCD) mainly reduces missed findings (false negatives).
    • Expert-informed decoding (ECD) mainly suppresses fabricated findings (false positives).
    • Removing both stages hurts performance most.
  • Evaluation combines lexical metrics (ROUGE-L, BLEU, BERTScore) with clinical ones (RadGraph-F1, Temporal-F1, RaTEScore, RadEval-BERT, CheXbert-F1). Tested models include MAIRA-2 and LLaVA-Med.
  • Expert ablations:
    • Swapping in MedSigLIP as the expert improves results consistently.
    • Restricting the expert to the top-5 symptoms lowers CheXbert-14 F1 by 1.68.
  • The guidance weights α and β give the best RadGraph-F1 at 0.5. Evaluation uses automatic metrics only, with no radiologist assessment.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of CambridgeCambridge · United Kingdom243 works · 121,396 citations🎓University of GlasgowGlasgow · United Kingdom11 works · 635 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksComputer Vision and Pattern Recognition · 2,869 worksMedicine · 241 worksHealth Informatics · 184 works

Cite

Cite as Xi Zhang, Zaiqiao Meng, Jake Lever and Edmond S. L. Ho. 2026. CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1755

@inproceedings{zhang2026ccd,
  title = {{CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding}},
  author = {Xi Zhang, Zaiqiao Meng, Jake Lever and Edmond S. L. Ho},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1755},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1755}
}

References

107 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Rawan AlSaad, Alaa Abd-Alrazaq, Sabri Boughorbel, Arfan Ahmed, Max-Antoine Renault, Rafat Damseh, and Javaid Sheikh. 2024. Multimodal large language models in health care: applications, challenges, and future outlook. Journal of medical Internet research, 26:e59505. find
  2. Wenbin An, Feng Tian, Sicong Leng, Jiahao Nie, Haonan Lin, QianYing Wang, Ping Chen, Xiaoqin Zhang, and Shijian Lu. 2025. Mitigating object hallucinations in large vision-language models with assembly of global and local attention. Preprint, arXiv:2406.12718. — [arXiv:2406.12718](https://arxiv.org/abs/2406.12718) find
  3. Ivo M Baltruschat, Hannes Nickisch, Michael Grass, Tobias Knopp, and Axel Saalbach. 2019. Comparison of deep learning approaches for multi-label chest x-ray classification. Scientific reports, 9(1):6381. find
  4. Oishi Banerjee, Hong-Yu Zhou, Subathra Adithan, Stephen Kwak, Kay Wu, and Pranav Rajpurkar. 2024. Direct preference optimization for suppressing hallucinated prior exams in radiology report generation. Preprint, arXiv:2406.06496. — [arXiv:2406.06496](https://arxiv.org/abs/2406.06496) find
  5. Shruthi Bannur, Kenza Bouzid, Daniel C. Castro, Anton Schwaighofer, Anja Thieme, Sam Bond-Taylor, Maximilian Ilse, Fernando Pérez-García, Valentina Salvatelli, Harshita Sharma, Felix Meissen, Mercy Ranjit, Shaury Srivastav, Julia Gong, Noel C. F. Codella, Fabian Falck, Ozan Oktay, Matthew P. Lungren… — [arXiv:2406.04449](https://arxiv.org/abs/2406.04449) find
  6. D. Barber. 2012. Bayesian Reasoning and Machine Learning. Bayesian Reasoning and Machine Learning. Cambridge University Press. find
  7. Pierre Chambon, Jean-Benoit Delbrouck, Thomas Sounack, Shih-Cheng Huang, Zhihong Chen, Maya Varma, Steven QH Truong, Chu The Chuong, and Curtis P. Langlotz. 2024. Chexpert plus: Augmenting a large chest x-ray dataset with text radiology reports, patient demographics and additional image formats. Pre… — [arXiv:2405.19538](https://arxiv.org/abs/2405.19538) find
  8. Boyuan Chen, Zhuo Xu, Sean Kirmani, Brian Ichter, Danny Driess, Pete Florence, Dorsa Sadigh, Leonidas Guibas, and Fei Xia. 2024a. Spatialvlm: Endowing vision-language models with spatial reasoning capabilities. Preprint, arXiv:2401.12168. find
  9. Jiawei Chen, Dingkang Yang, Tong Wu, Yue Jiang, Xiaolu Hou, Mingcheng Li, Shunli Wang, Dongling Xiao, Ke Li, and Lihua Zhang. 2024b. Detecting and evaluating medical hallucinations in large vision language models. Preprint, arXiv:2406.10185. — [arXiv:2406.10185](https://arxiv.org/abs/2406.10185) find
  10. Zeming Chen, Alejandro Hernández-Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne H… — MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
  11. Zhihong Chen, Maya Varma, Jean-Benoit Delbrouck, Magdalini Paschali, Louis Blankemeier, Dave Van Veen, Jeya Maria Jose Valanarasu, Alaa Youssef, Joseph Paul Cohen, Eduardo Pontes Reis, Emily B. Tsai, Andrew Johnston, Cameron Olsen, Tanishq Mathew Abraham, Sergios Gatidis, Akshay S Chaudhari, and Cur… — [arXiv:2401.12208](https://arxiv.org/abs/2401.12208) find
  12. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. find
  13. Joseph Paul Cohen, Joseph D. Viviano, Paul Bertin, Paul Morrison, Parsa Torabian, Matteo Guarrera, Matthew P Lungren, Akshay Chaudhari, Rupert Brooks, Mohammad Hashir, and Hadrien Bertrand. 2021. Torchxrayvision: A library of chest x-ray datasets and models. Preprint, arXiv:2111.00595. — [arXiv:2111.00595](https://arxiv.org/abs/2111.00595) find
  14. Jonathan J Deeks and Douglas G Altman. 2004. Diagnostic tests 4: likelihood ratios. Bmj, 329(7458):168– 169. find
  15. Jean-Benoit Delbrouck, Pierre Chambon, Christian Bluethgen, Emily Tsai, Omar Almusa, and Curtis Langlotz. 2022. Improving the factual correctness of radiology report generation with semantic rewards. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4348–4360, Abu Dhabi… find
  16. Dina Demner-Fushman, Marc D Kohli, Marc B Rosenman, Sonya E Shooshan, Laritza Rodriguez, Sameer Antani, George R Thoma, and Clement J McDonald. 2015. Preparing a collection of radiology examinations for distribution and retrieval. Journal of the American Medical Informatics Association, 23(2):304–31… find
  17. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. Preprint, arXiv:1810.04805.
  18. Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, and Stefano Soatto. 2024. Multi-modal hallucination control by visual information grounding. Preprint, arXiv:2403.14003. — [arXiv:2403.14003](https://arxiv.org/abs/2403.14003) find
  19. Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi, Oriol Nieto, Zeyu Jin, and Dinesh Manocha. 2025. Visual description grounding reduces hallucinations and boosts reasoning in lvlms. Preprint, arXiv:2405.15683. — [arXiv:2405.15683](https://arxiv.org/abs/2405.15683) find
  20. David A Grimes and Kenneth F Schulz. 2005. Refining clinical diagnosis with likelihood ratios. The Lancet, 365(9469):1500–1505. find
  21. Zishan Gu, Changchang Yin, Fenglin Liu, and Ping Zhang. 2024. Medvh: Towards systematic evaluation of hallucination for large vision language models in the medical context. Preprint, arXiv:2407.02730. — [arXiv:2407.02730](https://arxiv.org/abs/2407.02730) find
  22. Paul Hager, Friederike Jungmann, Robbie Holland, Kunal Bhagat, Inga Hubrecht, Manuel Knauer, Jakob Vielhauer, Marcus Makowski, Rickmer Braren, Georgios Kaissis, and 1 others. 2024. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nature medicine, 30(… find
  23. Wenjun Hou, Yi Cheng, Kaishuai Xu, Heng Li, Yan Hu, Wenjie Li, and Jiang Liu. 2025. Radar: Enhancing radiology report generation with supplementary knowledge injection. Preprint, arXiv:2505.14318. find
  24. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. Preprint, arXiv:2106.09685.
  25. Xinyue Hu, Lin Gu, Kazuma Kobayashi, Liangchen Liu, Mengliang Zhang, Tatsuya Harada, Ronald M Summers, and Yingying Zhu. 2024. Interpretable medical image visual question answering via multimodal relationship graph learning. Medical Image Analysis, 97:103279. find
  26. Jonathan Huang, Luke Neill, Matthew Wittbrodt, David Melnick, Matthew Klug, Michael Thompson, John Bailitz, Timothy Loftus, Sanjeev Malik, Amit Phull, and 1 others. 2023. Generative artificial intelligence for chest radiograph interpretation in the emergency department. JAMA network open, 6(10):e233… find
  27. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and 1 others. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems,…
  28. Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2024. Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. Preprint, arXiv:2311.17911. find
  29. Stephanie L. Hyland, Shruthi Bannur, Kenza Bouzid, Daniel C. Castro, Mercy Ranjit, Anton Schwaighofer, Fernando Pérez-García, Valentina Salvatelli, Shaury Srivastav, Anja Thieme, Noel Codella, Matthew P. Lungren, Maria Teodora Wetscherek, Ozan Oktay, and Javier Alvarez-Valle. 2024. Maira-1: A specia… — [arXiv:2311.13668](https://arxiv.org/abs/2311.13668) find
  30. Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, Jayne Seekins, David A. Mong, Safwan S. Halabi, Jesse K. Sandberg, Ricky Jones, David B. Larson, Curtis P. Langlotz, Bhavik N. Patel, Matthew P. Lu… find
  31. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  32. Yue Jiang, Jiawei Chen, Dingkang Yang, Mingcheng Li, Shunli Wang, Tong Wu, Ke Li, and Lihua Zhang. 2025a. Comt: Chain-of-medical-thought reduces hallucination in medical report generation. Preprint, arXiv:2406.11451. — [arXiv:2406.11451](https://arxiv.org/abs/2406.11451) find
  33. Zhangqi Jiang, Junkai Chen, Beier Zhu, Tingjin Luo, Yankun Shen, and Xu Yang. 2025b. Devils in middle layers of large vision-language models: Interpreting, detecting and mitigating object hallucinations via attention lens. Preprint, arXiv:2411.16724. — [arXiv:2411.16724](https://arxiv.org/abs/2411.16724) find
  34. Alistair E. W. Johnson, Tom J. Pollard, Nathaniel R. Greenbaum, Matthew P. Lungren, Chih ying Deng, Yifan Peng, Zhiyong Lu, Roger G. Mark, Seth J. Berkowitz, and Steven Horng. 2019a. Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs. Preprint, arXiv:1901.07042. — [arXiv:1901.07042](https://arxiv.org/abs/1901.07042) find
  35. Alistair EW Johnson, Tom J Pollard, Seth J Berkowitz, Nathaniel R Greenbaum, Matthew P Lungren, Chih-ying Deng, Roger G Mark, and Steven Horng. 2019b. Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data, 6(1):317. find
  36. Alistair EW Johnson, David J Stone, Leo A Celi, and Tom J Pollard. 2018. The mimic code repository: enabling reproducibility in critical care research. Journal of the American Medical Informatics Association, 25(1):32–39. find
  37. Yubin Kim, Hyewon Jeong, Shan Chen, Shuyue Stella Li, Chanwoo Park, Mingyu Lu, Kumail Alhamoud, Jimin Mun, Cristina Grau, Minseok Jung, Rodrigo Gameiro, Lizhou Fan, Eugene Park, Tristan Lin, Joonsik Yoon, Wonjin Yoon, Maarten Sap, Yulia Tsvetkov, Paul Liang, and 8 others. 2025. Medical hallucination… — [arXiv:2503.05777](https://arxiv.org/abs/2503.05777) find
  38. Yuxiang Lai, Jike Zhong, Ming Li, Shitian Zhao, and Xiaofeng Yang. 2025. Med-r1: Reinforcement learning for generalizable medical reasoning in vision-language models. Preprint, arXiv:2503.13939. — [arXiv:2503.13939](https://arxiv.org/abs/2503.13939) find
  39. Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, and Lidong Bing. 2023. Mitigating object hallucinations in large vision-language models through visual contrastive decoding. Preprint, arXiv:2311.16922.
  40. Binxu Li, Tiankai Yan, Yuanting Pan, Jie Luo, Ruiyang Ji, Jiayuan Ding, Zhe Xu, Shilong Liu, Haoyu Dong, Zihao Lin, and Yixin Wang. 2024. Mmedagent: Learning to use medical tools with multi-modal agent. Preprint, arXiv:2407.02483. find
  41. Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023a. LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day. In Thirty-seventh Conference on Neural Information Processing Systems Datasets…
  42. Geng Li, Jinglin Xu, Yunzhen Zhao, and Yuxin Peng. 2025a. Dyfo: A training-free dynamic focus visual search for enhancing lmms in fine-grained visual understanding. Preprint, arXiv:2504.14920. — [arXiv:2504.14920](https://arxiv.org/abs/2504.14920) find
  43. Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, and Mike Lewis. 2023b. Contrastive decoding: Open-ended text generation as optimization. Preprint, arXiv:2210.15097.
  44. Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, and Dimitris N. Metaxas. 2025b. The hidden life of tokens: Reducing hallucination of large vision-language models via visual information steering. Preprint, arXiv:2502.03628. — [arXiv:2502.03628](https://arxiv.org/abs/2502.03628) find
  45. Chia Xin Liang, Pu Tian, Caitlyn Heqi Yin, Yao Yua, Wei An-Hou, Li Ming, Xinyuan Song, Tianyang Wang, Ziqian Bi, and Ming Liu. 2025. A comprehensive survey and guide to multimodal large language models in vision-language tasks. Preprint, arXiv:2411.06284. — [arXiv:2411.06284](https://arxiv.org/abs/2411.06284) find
  46. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
  47. Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew Mc-Dermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, and Marzyeh Ghassemi. 2019. Clinically accurate chest x-ray report generation. Preprint, arXiv:1904.02633. find
  48. Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, and Wei Peng. 2024a. A survey on hallucination in large vision-language models. Preprint, arXiv:2402.00253. find
  49. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2024b. Improved baselines with visual instruction tuning. Preprint, arXiv:2310.03744.
  50. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Preprint, arXiv:2304.08485.
  51. Jiaxiang Liu, Yuan Wang, Jiawei Du, Joey Tianyi Zhou, and Zuozhu Liu. 2024c. Medcot: Medical chain of thought via hierarchical expert. Preprint, arXiv:2412.13736. find
  52. Sheng Liu, Haotian Ye, Lei Xing, and James Zou. 2024d. Reducing hallucinations in vision-language models via latent space steering. Preprint, arXiv:2410.15778. — [arXiv:2410.15778](https://arxiv.org/abs/2410.15778) find
  53. Shi Liu, Kecheng Zheng, and Wei Chen. 2024e. Paying more attention to image: A training-free method for alleviating hallucination in lvlms. Preprint, arXiv:2407.21771. — [arXiv:2407.21771](https://arxiv.org/abs/2407.21771) find
  54. Kyungmin Min, Minbeom Kim, Kang il Lee, Dongryeol Lee, and Kyomin Jung. 2025. Mitigating hallucinations in large vision-language models via summary-guided decoding. Preprint, arXiv:2410.13321. find
  55. Maram Mahmoud A Monshi, Josiah Poon, and Vera Chung. 2020. Deep learning in generating radiology reports: A survey. Artificial Intelligence in Medicine, 106:101878. find
  56. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others.… — GPT-4 Technical Report
  57. Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Edward Michalson Md, Michael Moseley, Curtis Langlotz, Akshay S Chaudhari, and Jean-Benoit Delbrouck. 2024. Green: Generative radiology report evaluation and error notation. In Findings of the Associat… find
  58. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, page 311–318, USA. Association for Computational Linguistics.
  59. Fernando Pérez-García, Harshita Sharma, Sam Bond-Taylor, Kenza Bouzid, Valentina Salvatelli, Maximilian Ilse, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Matthew P. Lungren, Maria Wetscherek, Noel Codella, Stephanie L. Hyland, Javier Alvarez-Valle, and Ozan Oktay. 2024. RAD-DINO: Exploring… — [arXiv:2401.10815](https://arxiv.org/abs/2401.10815) find
  60. Fernando Pérez-García, Harshita Sharma, Sam Bond-Taylor, Kenza Bouzid, Valentina Salvatelli, Maximilian Ilse, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Matthew P. Lungren, Maria Teodora Wetscherek, Noel Codella, Stephanie L. Hyland, Javier Alvarez-Valle, and Ozan Oktay. 2025. Exploring s… find
  61. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. Preprint, arXiv:2103.00020.
  62. Mercy Ranjit and Tanuja Ganu. 2025. Rad-phi4-vision-cxr: A compact multimodal assistant for versatile radiology workflows. In Machine Learning for Health Symposium 2025. Microsoft, Proceedings of Machine Learning Research (PMLR). find
  63. Carveth Read. 1910. Logic, Deductive and Inductive. A. Moring. find
  64. Khaled Saab, Jan Freyberg, Chunjong Park, Tim Strother, Yong Cheng, Wei-Hung Weng, David G. T. Barrett, David Stutz, Nenad Tomasev, Anil Palepu, Valentin Liévin, Yash Sharma, Roma Ruparel, Abdullah Ahmed, Elahe Vedadi, Kimberly Kanada, Cian Hughes, Yun Liu, Geoff Brown, and 17 others. 2025. Advancin… — [arXiv:2505.04653](https://arxiv.org/abs/2505.04653) find
  65. Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, and Aman Chadha. 2024. A comprehensive survey of hallucination in large language, image, video and audio foundation models. Preprint, arXiv:2405.09589. find
  66. Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri, Atilla Kiraly, Madeleine Traverse, Timo Kohlberger, Shawn Xu, Fayaz Jamil, Cían Hughes, Charles Lau, Justin Chen, Fereshteh Mahvar, Liron Yatziv, Tiffany Chen, Bram Sterling, Stefanie Anna Baby, Susanna Maria Baby, Jeremy Lai, Samuel Schmidgall, a… find
  67. Harshita Sharma, Maxwell C. Reynolds, Valentina Salvatelli, Anne-Marie G. Sykes, Kelly K. Horst, Anton Schwaighofer, Maximilian Ilse, Olesya Melnichenko, Sam Bond-Taylor, Fernando Pérez-García, Vamshi K. Mugu, Alex Chan, Ceylan Colak, Shelby A. Swartz, Motassem B. Nashawaty, Austin J. Gonzalez, Heat… — [arXiv:2511.21735](https://arxiv.org/abs/2511.21735) find
  68. Harshita Sharma, Valentina Salvatelli, Shaury Srivastav, Kenza Bouzid, Shruthi Bannur, Daniel C. Castro, Maximilian Ilse, Sam Bond-Taylor, Mercy Prasanna Ranjit, Fabian Falck, Fernando Pérez-García, Anton Schwaighofer, Hannah Richardson, Maria Wetscherek, Stephanie Hyland, and Javier Alvarez-Valle.… find
  69. Yiqiu Shen, Yanqi Xu, Jiajian Ma, Wushuang Rui, Chen Zhao, Laura Heacock, and Chenchan Huang. 2025. Multi-modal large language models in radiology: principles, applications, and potential. Abdominal Radiology, 50(6):2745–2757. find
  70. Peeyush Singhal, Rahee Walambe, Sheela Ramanna, and Ketan Kotecha. 2023. Domain adaptation: challenges, methods, datasets, and applications. IEEE access, 11:6973–7020. find
  71. Akshay Smit, Saahil Jain, Pranav Rajpurkar, Anuj Pareek, Andrew Y. Ng, and Matthew P. Lungren. 2020. Chexbert: Combining automatic labelers and expert annotations for accurate radiology report labeling using bert. Preprint, arXiv:2004.09167.
  72. Liwen Sun, James Zhao, Megan Han, and Chenyan Xiong. 2025. Fact-aware multimodal retrieval augmentation for accurate medical radiology report generation. Preprint, arXiv:2407.15268. find
  73. Feilong Tang, Chengzhi Liu, Zhongxing Xu, Ming Hu, Zelin Peng, Zhiwei Yang, Jionglong Su, Minquan Lin, Yifan Peng, Xuelian Cheng, Imran Razzak, and Zongyuan Ge. 2025. Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding. Preprint, arXiv:2505.16652. — [arXiv:2505.16652](https://arxiv.org/abs/2505.16652) find
  74. Fabio Tavora, Y Zhang, M Zhang, L Li, M Ripple, D Fowler, and Allen Burke. 2012. Cardiomegaly is a common arrhythmogenic substrate in adult sudden cardiac deaths, and is associated with obesity. Pathology-Journal of the RCPA, 44(3):187–191. find
  75. LASA Team, Weiwen Xu, Hou Pong Chan, Long Li, Mahani Aljunied, Ruifeng Yuan, Jianyu Wang, Chenghao Xiao, Guizhen Chen, Chaoqun Liu, Zhaodonghui Li, Yu Sun, Junao Shen, Chaojun Wang, Jie Tan, Deli Zhao, Tingyang Xu, Hao Zhang, and Yu Rong. 2025. Lingshu: A generalist foundation model for unified mult… — [arXiv:2506.07044](https://arxiv.org/abs/2506.07044) find
  76. S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, and Amitava Das. 2024. A comprehensive survey of hallucination mitigation techniques in large language models. Preprint, arXiv:2401.01313.
  77. Tao Tu, Shekoofeh Azizi, Danny Driess, Mike Schaekermann, Mohamed Amin, Pi-Chuan Chang, Andrew Carroll, Chuck Lau, Ryutaro Tanno, Ira Ktena, Basil Mustafa, Aakanksha Chowdhery, Yun Liu, Simon Kornblith, David Fleet, Philip Mansfield, Sushant Prakash, Renee Wong, Sunny Virmani, and 13 others. 2023. T… find
  78. Tao Tu, Mike Schaekermann, Anil Palepu, Khaled Saab, Jan Freyberg, Ryutaro Tanno, Amy Wang, Brenna Li, Mohamed Amin, Yong Cheng, and 1 others. 2025. Towards conversational diagnostic artificial intelligence. Nature, pages 1–9. find
  79. Chenxi Wang, Xiang Chen, Ningyu Zhang, Bozhong Tian, Haoming Xu, Shumin Deng, and Huajun Chen. 2025a. Mllm can see? dynamic correction decoding for hallucination mitigation. Preprint, arXiv:2410.11779. — [arXiv:2410.11779](https://arxiv.org/abs/2410.11779) find
  80. Jiaqi Wang, Hanqi Jiang, Yiheng Liu, Chong Ma, Xu Zhang, Yi Pan, Mengyuan Liu, Peiran Gu, Sichen Xia, Wenjun Li, Yutong Zhang, Zihao Wu, Zhengliang Liu, Tianyang Zhong, Bao Ge, Tuo Zhang, Ning Qiang, Xintao Hu, Xi Jiang, and 5 others. 2024a. A comprehensive review of multimodal large language models… — [arXiv:2408.01319](https://arxiv.org/abs/2408.01319) find
  81. Wenxuan Wang, Zizhan Ma, Zheng Wang, Chenghan Wu, Jiaming Ji, Wenting Chen, Xiang Li, and Yixuan Yuan. 2025b. A survey of llm-based agents in medicine: How far are we from baymax? Preprint, arXiv:2502.11211. find
  82. Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, and Ronald M. Summers. 2018. Tienet: Text-image embedding network for common thorax disease classification and reporting in chest x-rays. Preprint, arXiv:1801.04334. — [arXiv:1801.04334](https://arxiv.org/abs/1801.04334) find
  83. Xintong Wang, Jingheng Pan, Liang Ding, and Chris Biemann. 2024b. Mitigating hallucinations in large vision-language models with instruction contrastive decoding. Preprint, arXiv:2403.18715. find
  84. Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Nathan Cooper, Griffin Adams, Jeremy Howard, and Iacopo Poli. 2024. Smarter, better, faster, longer: A modern bidirectional encoder for fast,…
  85. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, and 3 others. 2020. Transf…
  86. Sangmin Woo, Donguk Kim, Jaehyuk Jang, Yubin Choi, and Changick Kim. 2025. Don’t miss the forest for the trees: Attentional vision calibration for large vision language models. Preprint, arXiv:2405.17820. find
  87. John H Woodring and James C Reed. 1996. Types and mechanisms of pulmonary atelectasis. Journal of thoracic imaging, 11(2):92–108. find
  88. Chaoyi Wu, Jiayu Lei, Qiaoyu Zheng, Weike Zhao, Weixiong Lin, Xiaoman Zhang, Xiao Zhou, Ziheng Zhao, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Can gpt-4v(ision) serve medical applications? case studies on gpt-4v for multimodal medical diagnosis. Preprint, arXiv:2310.09909. — [arXiv:2310.09909](https://arxiv.org/abs/2310.09909) find
  89. Jinge Wu, Yunsoo Kim, and Honghan Wu. 2024. Hallucination benchmark in medical visual question answering. Preprint, arXiv:2401.05827. — [arXiv:2401.05827](https://arxiv.org/abs/2401.05827) find
  90. Peng Xia, Kangyu Zhu, Haoran Li, Tianze Wang, Weijia Shi, Sheng Wang, Linjun Zhang, James Zou, and Huaxiu Yao. 2025. Mmed-rag: Versatile multimodal rag system for medical vision language models. Preprint, arXiv:2410.13085. — [arXiv:2410.13085](https://arxiv.org/abs/2410.13085) find
  91. Justin Xu, Xi Zhang, Javid Abderezaei, Julie Bauml, Roger Boodoo, Fatemeh Haghighi, Ali Ganjizadeh, Eric Brattain, Dave Van Veen, Zaiqiao Meng, David W Eyre, and Jean-Benoit Delbrouck. 2025a. RadEval: A framework for radiology text evaluation. In Proceedings of the 2025 Conference on Empirical Metho… find
  92. Xinhao Xu, Hui Chen, Mengyao Lyu, Sicheng Zhao, Yizhe Xiong, Zijia Lin, Jungong Han, and Guiguang Ding. 2025b. Mitigating hallucinations in multimodal large language models via image token attention-guided decoding. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the… find
  93. Nur Yildirim, Hannah Richardson, Maria Teodora Wetscherek, Junaid Bajwa, Joseph Jacob, Mark Ames Pinnock, Stephen Harris, Daniel Coelho De Castro, Shruthi Bannur, Stephanie Hyland, Pratik Ghosh, Mercy Ranjit, Kenza Bouzid, Anton Schwaighofer, Fernando Pérez-García, Harshita Sharma, Ozan Oktay, Matth… find
  94. Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2024. A survey on multimodal large language models. National Science Review, 11(12):nwae403.
  95. Juan Manuel Zambrano Chaves, Shih-Cheng Huang, Yanbo Xu, Hanwen Xu, Naoto Usuyama, Sheng Zhang, Fei Wang, Yujia Xie, Mahmoud Khademi, Ziyi Yang, Hany Awadalla, Julia Gong, Houdong Hu, Jianwei Yang, Chunyuan Li, Jianfeng Gao, Yu Gu, Cliff Wong, Mu Wei, and 8 others. 2025. A clinically accessible smal… find
  96. Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. 2023. Sigmoid loss for language image pre-training. Preprint, arXiv:2303.15343.
  97. Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, and Filip Ilievski. 2025a. Mllms know where to look: Training-free perception of small visual details with multimodal llms. Preprint, arXiv:2502.17422. — [arXiv:2502.17422](https://arxiv.org/abs/2502.17422) find
  98. Sheng Zhang, Yanbo Xu, Naoto Usuyama, Hanwen Xu, Jaspreet Bagga, Robert Tinn, Sam Preston, Rajesh Rao, Mu Wei, Naveen Valluri, Cliff Wong, Andrea Tupini, Yu Wang, Matt Mazzola, Swadheen Shukla, Lars Liden, Jianfeng Gao, Angela Crabtree, Brian Piening, and 5 others. 2025b. Biomedclip: a multimodal bi… find
  99. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. Preprint, arXiv:1904.09675. find
  100. Xi Zhang, Zaiqiao Meng, Jake Lever, and Edmond S. L. Ho. 2025c. Libra: Leveraging temporal images for biomedical radiology analysis. In Findings of the Association for Computational Linguistics: ACL 2025, pages 17275–17303, Vienna, Austria. Association for Computational Linguistics. find
  101. Xi Zhang, Zaiqiao Meng, Jake Lever, and Edmond SL Ho. 2024a. Gla-ai4biomed at rrg24: Visual instruction-tuned adaptation for radiology report generation. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 624– 634. find
  102. Xiaoman Zhang, Julian Nicolas Acosta, Xiaoli Yang, Subathra Adithan, Luyang Luo, Hong-Yu Zhou, Joshua Miller, Ouwen Huang, Zongwei Zhou, Ibrahim Ethem Hamamci, Shruthi Bannur, Kenza Bouzid, Xi Zhang, Zaiqiao Meng, Aaron Nicolson, Bevan Koopman, Inhyeok Baek, Hanbin Ko, Mercy Prasanna Ranjit, and 3 o… find
  103. Biocomputing 2026: Proceedings of the Pacific Symposium, pages 236–250. find
  104. Xiaoman Zhang, Hong-Yu Zhou, Xiaoli Yang, Oishi Banerjee, Julián N. Acosta, Josh Miller, Ouwen Huang, and Pranav Rajpurkar. 2024b. Rexrank: A public leaderboard for ai-powered radiology report generation. Preprint, arXiv:2411.15122. — [arXiv:2411.15122](https://arxiv.org/abs/2411.15122) find
  105. Linxi Zhao, Yihe Deng, Weitong Zhang, and Quanquan Gu. 2025. Mitigating object hallucination in large vision-language models via image-grounded guidance. Preprint, arXiv:2402.08680. — [arXiv:2402.08680](https://arxiv.org/abs/2402.08680) find
  106. Weike Zhao, Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2024. RaTEScore: A metric for radiology report generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15004–15019, Miami, Florida, USA. Association for Computational Lin… find
  107. Zhihong Zhu, Yunyan Zhang, Xianwei Zhuang, Fan Zhang, Zhongwei Wan, Yuyan Chen, QingqingLong QingqingLong, Yefeng Zheng, and Xian Wu. 2025. Can we trust AI doctors? a survey of medical hallucination in large language and large vision-language models. In Findings of the Association for Computational… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-ccd-mitigating-hallucinations-radiology-mllms/