{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:38:06Z","timestamp":1767418686668,"version":"3.48.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032049803"},{"type":"electronic","value":"9783032049810"}],"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\/978-3-032-04981-0_9","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:13:18Z","timestamp":1758258798000},"page":"88-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BiasICL: In-Context Learning and\u00a0Demographic Biases of\u00a0Vision Language Models"],"prefix":"10.1007","author":[{"given":"Sonnet","family":"Xu","sequence":"first","affiliation":[]},{"given":"Joseph D.","family":"Janizek","sequence":"additional","affiliation":[]},{"given":"Yixing","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Roxana","family":"Daneshjou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"9_CR1","unstructured":"Awadalla, A., et\u00a0al.: Openflamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Banerjee, I., et al.: \u201cshortcuts\u201d causing bias in radiology artificial intelligence: causes, evaluation and mitigation. J. Am. Coll. Radiol. (2023)","DOI":"10.1016\/j.jacr.2023.06.025"},{"key":"9_CR3","unstructured":"Biderman, S., et\u00a0al.: Lessons from the trenches on reproducible evaluation of language models. arXiv preprint arXiv:2405.14782 (2024)"},{"key":"9_CR4","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. CoRR (2020) arXiv:2005.14165"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Daneshjou, et\u00a0al.: Disparities in dermatology ai performance on a diverse, curated clinical image set. Sci. Adv. 8(31), eabq6147 (2022)","DOI":"10.1126\/sciadv.abq6147"},{"issue":"7","key":"9_CR6","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","volume":"3","author":"AJ DeGrave","year":"2021","unstructured":"DeGrave, A.J., Janizek, J.D., Lee, S.I.: Ai for radiographic covid-19 detection selects shortcuts over signal. Nat. Mach. Intell. 3(7), 610\u2013619 (2021)","journal-title":"Nat. Mach. Intell."},{"issue":"22","key":"9_CR7","doi-asserted-by":"publisher","first-page":"2083","DOI":"10.1056\/NEJMsa2311809","volume":"390","author":"JA Diao","year":"2024","unstructured":"Diao, J.A., et al.: Implications of race adjustment in lung-function equations. N. Engl. J. Med. 390(22), 2083 (2024)","journal-title":"N. Engl. J. Med."},{"issue":"1","key":"9_CR8","doi-asserted-by":"publisher","first-page":"10104","DOI":"10.1038\/s41467-024-51465-9","volume":"15","author":"D Ferber","year":"2024","unstructured":"Ferber, D., et al.: In-context learning enables multimodal large language models to classify cancer pathology images. Nat. Commun. 15(1), 10104 (2024)","journal-title":"Nat. Commun."},{"issue":"6","key":"9_CR9","doi-asserted-by":"publisher","first-page":"e406","DOI":"10.1016\/S2589-7500(22)00063-2","volume":"4","author":"JW Gichoya","year":"2022","unstructured":"Gichoya, J.W., et al.: Ai recognition of patient race in medical imaging: a modelling study. Lancet Digital Health 4(6), e406\u2013e414 (2022)","journal-title":"Lancet Digital Health"},{"key":"9_CR10","unstructured":"Gupta, K., et al.: How robust are llms to in-context majority label bias? arXiv preprint arXiv:2312.16549 (2023)"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Irvin, J., et\u00a0al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 590\u2013597 (2019). https:\/\/doi.org\/10.71718\/y7pj-4v93","DOI":"10.71718\/y7pj-4v93"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Janizek, J.D., Erion, G., DeGrave, A.J., Lee, S.I.: An adversarial approach for the robust classification of pneumonia from chest radiographs. In: Proceedings of the ACM Conference on Health, Inference, and Learning, pp. 69\u201379 (2020)","DOI":"10.1145\/3368555.3384458"},{"key":"9_CR13","unstructured":"Jiang, Y., Irvin, J., Wang, J.H., Chaudhry, M.A., Chen, J.H., Ng, A.Y.: Many-shot in-context learning in multimodal foundation models. arXiv preprint arXiv:2405.09798 (2024)"},{"key":"9_CR14","unstructured":"Laurent, J.M., et al.: Lab-bench: measuring capabilities of language models for biology research. arXiv preprint arXiv:2407.10362 (2024)"},{"key":"9_CR15","unstructured":"Mirza, A., et\u00a0al.: Are large language models superhuman chemists? arXiv preprint arXiv:2404.01475 (2024)"},{"issue":"1","key":"9_CR16","doi-asserted-by":"publisher","first-page":"8621","DOI":"10.1038\/s41598-021-86577-5","volume":"11","author":"MR Munk","year":"2021","unstructured":"Munk, M.R., Kurmann, T., Marquez-Neila, P., Zinkernagel, M.S., Wolf, S., Sznitman, R.: Assessment of patient specific information in the wild on fundus photography and optical coherence tomography. Sci. Rep. 11(1), 8621 (2021)","journal-title":"Sci. Rep."},{"key":"9_CR17","unstructured":"Nori, H., et\u00a0al.: Can generalist foundation models outcompete special-purpose tuning? case study in medicine. arXiv preprint arXiv:2311.16452 (2023)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Oakden-Rayner, L., Dunnmon, J., Carneiro, G., R\u00e9, C.: Hidden stratification causes clinically meaningful failures in machine learning for medical imaging. In: Proceedings of the ACM Conference on Health, Inference, and Learning, pp. 151\u2013159 (2020)","DOI":"10.1145\/3368555.3384468"},{"issue":"1","key":"9_CR19","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41746-023-00939-z","volume":"6","author":"JA Omiye","year":"2023","unstructured":"Omiye, J.A., Lester, J.C., Spichak, S., Rotemberg, V., Daneshjou, R.: Large language models propagate race-based medicine. NPJ Dig. Med. 6(1), 195 (2023)","journal-title":"NPJ Dig. Med."},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Seyyed-Kalantari, L., Liu, G., McDermott, M., Chen, I.Y., Ghassemi, M.: Chexclusion: fairness gaps in deep chest x-ray classifiers. In: BIOCOMPUTING 2021: Proceedings of the Pacific Symposium, pp. 232\u2013243. World Scientific (2020)","DOI":"10.1142\/9789811232701_0022"},{"key":"9_CR21","unstructured":"Wu, P., Liu, C., Chen, C., Li, J., Bercea, C.I., Arcucci, R.: Fmbench: benchmarking fairness in multimodal large language models on medical tasks. arXiv preprint arXiv:2410.01089 (2024)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Demographic bias of expert-level vision-language foundation models in medical imaging. arXiv preprint arXiv:2402.14815 (2024)","DOI":"10.1126\/sciadv.adq0305"},{"issue":"5","key":"9_CR23","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1007\/s10140-021-01953-y","volume":"28","author":"PH Yi","year":"2021","unstructured":"Yi, P.H., et al.: Radiology \u201cforensics\u2019\u2019: determination of age and sex from chest radiographs using deep learning. Emerg. Radiol. 28(5), 949\u2013954 (2021). https:\/\/doi.org\/10.1007\/s10140-021-01953-y","journal-title":"Emerg. Radiol."},{"issue":"11","key":"9_CR24","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":"9_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: A study on the calibration of in-context learning (2024). arxiv:2312.04021","DOI":"10.18653\/v1\/2023.findings-emnlp.152"},{"key":"9_CR26","unstructured":"Zhao, Z., Wallace, E., Feng, S., Klein, D., Singh, S.: Calibrate before use: improving few-shot performance of language models. In: International Conference on Machine Learning, pp. 12697\u201312706. PMLR (2021)"},{"key":"9_CR27","unstructured":"Zhou, H., et al.: Batch calibration: rethinking calibration for in-context learning and prompt engineering. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=L3FHMoKZcS"},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Zu, W., Xie, S., Zhao, Q., Li, G., Ma, L.: Embedded prompt tuning: towards enhanced calibration of pretrained models for medical images. Med. Image Anal. 97, 103258 (2024). https:\/\/doi.org\/10.1016\/j.media.2024.103258. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S136184152400183X","DOI":"10.1016\/j.media.2024.103258"}],"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\/978-3-032-04981-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:33:19Z","timestamp":1767418399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04981-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049803","9783032049810"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04981-0_9","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":"SX and JJ have no competing interests to declare that\u00a0are relevant to the content of this article. RD has served as an advisor to MDAlgorithms, Pair, and Revea and received consulting fees from Pfizer, L\u2019Oreal, Frazier Healthcare Partners, and DWA, and research funding from UCB and declares no non-financial competing interests.","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"}}]}}