{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:10:19Z","timestamp":1788945019837,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370976","type":"print"},{"value":"9783032370983","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37098-3_29","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:00:47Z","timestamp":1788944447000},"page":"529-546","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Reliable Medical Large Vision-Language Models via\u00a0Counterfactual Preference Optimization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9554-2133","authenticated-orcid":false,"given":"Xiaoguang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naipeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9346-6921","authenticated-orcid":false,"given":"Kartik","family":"Patwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3208-9075","authenticated-orcid":false,"given":"Lianlong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2772-387X","authenticated-orcid":false,"given":"Chen-Nee","family":"Chuah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxin","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"29_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"29_CR2","unstructured":"Bai, Y., et al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)"},{"key":"29_CR3","unstructured":"Banerjee, O., Zhou, H.Y., Wu, K., Adithan, S., Kwak, S., Rajpurkar, P.: Direct preference optimization for suppressing hallucinated prior exams in radiology report generation. In: Machine Learning for Healthcare Conference. PMLR (2024)"},{"key":"29_CR4","unstructured":"Bannur, S., et al.: Maira-2: grounded radiology report generation. arXiv preprint arXiv:2406.04449 (2024)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika 39(3\/4), 324\u2013345 (1952)","DOI":"10.1093\/biomet\/39.3-4.324"},{"key":"29_CR6","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Advances in Neural Information Processing Systems (2017)"},{"key":"29_CR7","unstructured":"Cui, C., et al.: Holistic analysis of hallucination in gpt-4v(ision): bias and interference challenges. arXiv preprint arXiv:2311.03287 (2023)"},{"issue":"2","key":"29_CR8","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2015","unstructured":"Demner-Fushman, D., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304\u2013310 (2015)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"29_CR9","unstructured":"Ethayarajh, K., Xu, W., Muennighoff, N., Jurafsky, D., Kiela, D.: KTO: model alignment as prospect theoretic optimization. arXiv preprint arXiv:2402.01306 (2024)"},{"key":"29_CR10","unstructured":"Hein, D., et al.: Preference fine-tuning for factuality in chest X-ray interpretation models without human feedback (2024)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hong, J., Lee, N., Thorne, J.: Reference-free monolithic preference optimization with odds ratio. arXiv preprint arXiv:2403.076916 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.626"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"29_CR13","unstructured":"Jain, S., et al.: Radgraph: extracting clinical entities and relations from radiology reports (2021)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"1","key":"29_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"29_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Abacha, A.B., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5, 180251 (2018)","journal-title":"Sci. Data"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., Wong, C.Y., Zhang, S., Usuyama, N., Poon, H., Gao, J.: Llava-med: training a large language and vision assistant for biomedicine in one day. In: NeurIPS Datasets and Benchmarks Track (2023)","DOI":"10.52202\/075280-1240"},{"issue":"12","key":"29_CR18","doi-asserted-by":"publisher","first-page":"8842","DOI":"10.1109\/TKDE.2024.3424268","volume":"36","author":"S Li","year":"2024","unstructured":"Li, S., Xue, F., Liu, K., Guo, D., Hong, R.: Multimodal graph causal embedding for multimedia-based recommendation. IEEE Trans. Knowl. Data Eng. 36(12), 8842\u20138858 (2024)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/075280-1516"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"29_CR22","unstructured":"Liu, J., et al.: Multimodal large language models in medicine and nursing: a survey. Authorea Preprints"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Liu, L., et al.: A causal adjustment module for debiasing scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3537283"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Liu, R., Liu, H., Li, G., Hou, H., Yu, T., Yang, T.: Contextual debiasing for visual recognition with causal mechanisms. In: CVPR, pp. 12755\u201312765 (2022)","DOI":"10.1109\/CVPR52688.2022.01242"},{"key":"29_CR25","unstructured":"Liu, S., et al.: A survey of direct preference optimization. arXiv preprint arXiv:2503.11701 (2025)"},{"key":"29_CR26","unstructured":"Liu, T., et al.: Statistical rejection sampling improves preference optimization. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: CRCL: causal representation consistency learning for anomaly detection in surveillance videos. IEEE Trans. Image Process. (2025)","DOI":"10.1109\/TIP.2025.3558089"},{"issue":"1","key":"29_CR28","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024)","journal-title":"Nat. Commun."},{"key":"29_CR29","doi-asserted-by":"publisher","first-page":"124198","DOI":"10.52202\/079017-3946","volume":"37","author":"Y Meng","year":"2024","unstructured":"Meng, Y., Xia, M., Chen, D.: Simpo: simple preference optimization with a reference-free reward. Adv. Neural. Inf. Process. Syst. 37, 124198\u2013124235 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR30","unstructured":"Moor, M., Huang, Q., Wu, S.H., Dalmia, M., Leskovec, J., Rajpurkar, P.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367 (2023)"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"29_CR32","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Pearl, J.: Causality. Cambridge University Press (2009)","DOI":"10.1017\/CBO9780511803161"},{"issue":"4","key":"29_CR34","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1037\/a0036434","volume":"19","author":"J Pearl","year":"2014","unstructured":"Pearl, J.: Interpretation and identification of causal mediation. Psychol. Methods 19(4), 459 (2014)","journal-title":"Psychol. Methods"},{"key":"29_CR35","unstructured":"Pearl, J., Glymour, M., Jewell, N.P.: Causal Inference in Statistics: A Primer. Wiley (2016)"},{"key":"29_CR36","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR37","unstructured":"Royer, C., Menze, B., Sekuboyina, A.: Multimedeval: a benchmark and toolkit for evaluating medical vision language models. arXiv preprint arXiv:2402.09262 (2024)"},{"key":"29_CR38","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"29_CR39","unstructured":"Sellergren, A., et al.: Medgemma technical report. arXiv preprint arXiv:2507.05201 (2025)"},{"issue":"11","key":"29_CR40","doi-asserted-by":"publisher","first-page":"6477","DOI":"10.1109\/TKDE.2024.3389668","volume":"36","author":"F Shao","year":"2024","unstructured":"Shao, F., Luo, Y., Gao, F., Yang, Y., Xiao, J.: Knowledge-guided causal intervention for weakly-supervised object localization. IEEE Trans. Knowl. Data Eng. 36(11), 6477\u20136489 (2024)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Sun, G., Qin, C., Fu, H., Wang, L., Tao, Z.: Stllava-med: self-training large language and vision assistant for medical question-answering. arXiv preprint arXiv:2406.19973 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1119"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Thirunavukarasu, A.J., et al.: Large language models in medicine. Nat. Med. 29(8), 1930\u20131940 (2023)","DOI":"10.1038\/s41591-023-02448-8"},{"key":"29_CR43","unstructured":"Wang, C., et al.: Beyond reward hacking: causal rewards for large language model alignment. arXiv preprint arXiv:2501.09620 (2025)"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: MDPO: conditional preference optimization for multimodal large language models. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 8078\u20138088 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.460"},{"issue":"10","key":"29_CR45","doi-asserted-by":"publisher","first-page":"9836","DOI":"10.1109\/TKDE.2022.3159802","volume":"35","author":"X Wang","year":"2022","unstructured":"Wang, X., Li, Q., Yu, D., Cui, P., Wang, Z., Xu, G.: Causal disentanglement for semantic-aware intent learning in recommendation. IEEE Trans. Knowl. Data Eng. 35(10), 9836\u20139849 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"11","key":"29_CR46","doi-asserted-by":"publisher","first-page":"11153","DOI":"10.1109\/TKDE.2022.3231352","volume":"35","author":"Y Wei","year":"2022","unstructured":"Wei, Y., Wang, X., Nie, L., Li, S., Wang, D., Chua, T.S.: Causal inference for knowledge graph based recommendation. IEEE Trans. Knowl. Data Eng. 35(11), 11153\u201311164 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"29_CR47","unstructured":"Wu, Y., Sun, Z., Yuan, H., Ji, K., Yang, Y., Gu, Q.: Self-play preference optimization for language model alignment. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Xu, W., et al.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning. arXiv preprint arXiv:2506.07044 (2025)","DOI":"10.1109\/TPAMI.2026.3730310"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Xu, Z., Li, Q., Nie, W., Wang, W., Liu, A.: Structure causal models and LLMs integration in medical visual question answering. IEEE Trans. Med. Imaging (2025)","DOI":"10.1109\/TMI.2025.3564320"},{"issue":"4","key":"29_CR50","doi-asserted-by":"publisher","DOI":"10.1148\/rg.230079","volume":"44","author":"A Yamada","year":"2024","unstructured":"Yamada, A., et al.: Pictorial review of pleural disease: multimodality imaging and differential diagnosis. Radiographics 44(4), e230079 (2024)","journal-title":"Radiographics"},{"issue":"11","key":"29_CR51","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002683","volume":"15","author":"JR Zech","year":"2018","unstructured":"Zech, J.R., Badgeley, M.A., Liu, M., Costa, A.B., Titano, J.J., Oermann, E.K.: Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med. 15(11), e1002683 (2018)","journal-title":"PLoS Med."},{"key":"29_CR52","unstructured":"Zhang, X., et al.: PMC-VQA: visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"},{"key":"29_CR53","unstructured":"Zheng, X., et al.: MLLMs are deeply affected by modality bias. arXiv preprint arXiv:2505.18657 (2025)"},{"key":"29_CR54","unstructured":"Zhi, H., Chen, P., Yao, H.: Medgr2: generative reward learning for robust medical reasoning. arXiv preprint arXiv:2501.05173 (2025)"},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, K., Jiang, M., Gabrys, B., Xu, Y.: Learning causal representations based on a GAE embedded autoencoder. IEEE Trans. Knowl. Data Eng. (2025)","DOI":"10.1109\/TKDE.2025.3546607"},{"key":"29_CR56","unstructured":"Zhou, Y., Cui, C., Rafailov, R., Finn, C., Yao, H.: Aligning modalities in vision large language models via preference fine-tuning. In: ICLR 2024 Workshop on Reliable and Responsible Foundation Models (2024)"},{"key":"29_CR57","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"29_CR58","unstructured":"Zhu, K., Xia, P., Li, Y., Zhu, H., Wang, S., Yao, H.: Mmedpo: aligning medical vision language models with clinical-aware multimodal preference optimization. In: International Conference on Machine Learning (ICML) (2025)"},{"key":"29_CR59","unstructured":"Zhu, X., et al.: Causal debiasing medical multimodal representation learning with missing modalities. arXiv preprint arXiv:2509.05615 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37098-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:01:06Z","timestamp":1788944466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37098-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370976","9783032370983"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37098-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}