{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T06:48:32Z","timestamp":1758350912473,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032051400"},{"type":"electronic","value":"9783032051417"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-05141-7_32","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:17:48Z","timestamp":1758269868000},"page":"325-335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowing or\u00a0Guessing? Robust Medical Visual Question Answering via\u00a0Joint Consistency and\u00a0Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Songtao","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sibo","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeying","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuozhu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"32_CR1","unstructured":"Abdin, M., et\u00a0al.: Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Bazi, Y., Rahhal, M.M.A., Bashmal, L., Zuair, M.: Vision\u2013language model for visual question answering in medical imagery. Bioengineering (2023)","DOI":"10.3390\/bioengineering10030380"},{"key":"32_CR3","unstructured":"Bellagente, M., et\u00a0al.: Stable lm 2 1.6 b technical report. arXiv preprint arXiv:2402.17834 (2024)"},{"key":"32_CR4","unstructured":"Chen, J., et al.: Huatuogpt-o1, towards medical complex reasoning with llms (2024). https:\/\/arxiv.org\/abs\/2412.18925"},{"key":"32_CR5","unstructured":"Chen, J., et al.: Huatuogpt-vision, towards injecting medical visual knowledge into multimodal llms at scale (2024). https:\/\/arxiv.org\/abs\/2406.19280"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: Temporal cycle-consistency learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00190"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: Pubmedclip: how much does clip benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023, pp. 1151\u20131163 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"32_CR9","unstructured":"Hurst, A., et\u00a0al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"32_CR10","unstructured":"Jiang, S., et\u00a0al.: Capo: Reinforcing consistent reasoning in medical decision-making. arXiv preprint arXiv:2506.12849 (2025)"},{"key":"32_CR11","unstructured":"Jiang, S., et al.: Omniv-med: Scaling medical vision-language model for universal visual understanding. arXiv preprint arXiv:2504.14692 (2025)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, S., et al.: Hscr: hierarchical self-contrastive rewarding for aligning medical vision language models. arXiv preprint arXiv:2506.00805 (2025)","DOI":"10.18653\/v1\/2025.acl-long.679"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, S., Zheng, T., Zhang, Y., Jin, Y., Yuan, L., Liu, Z.: Med-moe: mixture of domain-specific experts for lightweight medical vision-language models. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 3843\u20133860 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.221"},{"key":"32_CR14","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"32_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":"32_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., Tan, L., Liao, J., Zhong, S.: Self-supervised vision-language pretraining for medical visual question answering. arXiv preprint arXiv:2211.13594 (2022)","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"32_CR18","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":"32_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26296\u201326306 (June 2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, Y., Du, J., Zhou, J.T., Liu, Z.: Medcot: Medical chain of thought via hierarchical expert. arXiv preprint arXiv:2412.13736 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.962"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Z., Xu, D., Zhou, L.: Q2atransformer: Improving medical vqa via an answer querying decoder. arXiv preprint arXiv:2304.01611 (2023)","DOI":"10.1007\/978-3-031-34048-2_34"},{"key":"32_CR22","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. PMLR (2023)"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Ray, A., Sikka, K., Divakaran, A., Lee, S., Burachas, G.: Sunny and dark outside?! improving answer consistency in vqa through entailed question generation. arXiv preprint arXiv:1909.04696 (2019)","DOI":"10.18653\/v1\/D19-1596"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6649\u20136658 (2019)","DOI":"10.1109\/CVPR.2019.00681"},{"key":"32_CR25","unstructured":"Singhal, K., et\u00a0al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"van Sonsbeek, T., Derakhshani, M.M., Najdenkoska, I., Snoek, C.G., Worring, M.: Open-ended medical visual question answering through prefix tuning of language models. arXiv preprint arXiv:2303.05977 (2023)","DOI":"10.1007\/978-3-031-43904-9_70"},{"key":"32_CR27","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":"32_CR28","doi-asserted-by":"crossref","unstructured":"Sun, G., Qin, C., Wang, J., Chen, Z., Xu, R., Tao, Z.: Sq-llava: Self-questioning for large vision-language assistant. In: European Conference on Computer Vision, pp. 156\u2013172. Springer (2025)","DOI":"10.1007\/978-3-031-72673-6_9"},{"key":"32_CR29","unstructured":"Zhang, K., et\u00a0al.: Biomedgpt: a unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks. arXiv preprint arXiv:2305.17100 (2023)"},{"key":"32_CR30","unstructured":"Zhang, S., et\u00a0al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"32_CR31","unstructured":"Zhang, X., Wu, C., Zhao, Z., Lin, W., Zhang, Y., Wang, Y., Xie, W.: Pmc-vqa: Visual instruction tuning for medical visual question answering. arXiv preprint arXiv:2305.10415 (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05141-7_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:18:02Z","timestamp":1758269882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05141-7_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051400","9783032051417"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05141-7_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Yang Feng is employed by Angelalign Technology Inc.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}