{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T13:23:33Z","timestamp":1781270613790,"version":"3.54.1"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BioData Mining"],"DOI":"10.1186\/s13040-026-00518-4","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T04:29:44Z","timestamp":1770265784000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A crisis of overconfidence: Why confidence, not accuracy, is the real risk in clinical AI"],"prefix":"10.1186","volume":"19","author":[{"given":"Jacob S.","family":"Berkowitz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jake R.","family":"Patock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asma","family":"Nawaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Graciela","family":"Gonzalez-Hernandez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas P.","family":"Tatonetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"518_CR1","doi-asserted-by":"publisher","first-page":"e66917","DOI":"10.2196\/66917","volume":"13","author":"M Omar","year":"2025","unstructured":"Omar M, Agbareia R, Glicksberg BS, Nadkarni GN, Klang E. Benchmarking the confidence of large Language models in answering clinical questions: Cross-Sectional evaluation study. JMIR Med Inf. 2025;13:e66917\u201366917.","journal-title":"JMIR Med Inf"},{"key":"518_CR2","unstructured":"OpenAI, Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, et al. GPT-4 technical report. 2023; Available from: http:\/\/arxiv.org\/abs\/2303.08774."},{"key":"518_CR3","unstructured":"Xiao J, Hou B, Wang Z, Jin R, Long Q, Su WJ, et al. Restoring calibration for aligned large language models: a calibration-aware fine-tuning approach. 2025."},{"key":"518_CR4","doi-asserted-by":"crossref","unstructured":"Wang Z, Shi Z, Zhou H, Gao S, Sun Q, Li J. Towards Objective fine-tuning: how LLMs\u2019 prior knowledge causes potential poor calibration? in: proceedings of the 63rd annual meeting of the association for computational linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics. 2025;1:14830\u201353.","DOI":"10.18653\/v1\/2025.acl-long.722"},{"key":"518_CR5","unstructured":"Guo C, Pleiss G, Sun Y, Weinberger KQ. On calibration of modern neural networks. 2017."},{"key":"518_CR6","unstructured":"Minderer M, Djolonga J, Romijnders R, Hubis F, Zhai X, Houlsby N et al. Revisiting the calibration of modern neural networks. 2021."},{"key":"518_CR7","unstructured":"Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif. 1999."},{"key":"518_CR8","doi-asserted-by":"crossref","unstructured":"Spiess C, Gros D, Pai KS, Pradel M, Rabin MRI, Alipour A et al. Calibration and correctness of language models for code. In: 2025 IEEE\/ACM 47th international conference on software engineering (ICSE). IEEE. 2025;540\u201352.","DOI":"10.1109\/ICSE55347.2025.00040"},{"key":"518_CR9","doi-asserted-by":"crossref","unstructured":"Zadrozny B, Elkan C. Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. New York, NY, USA: ACM. 2002;694\u20139.","DOI":"10.1145\/775047.775151"},{"key":"518_CR10","doi-asserted-by":"crossref","unstructured":"Berkowitz J, Kivelson S, Srinivasan A, Gisladottir U, Tsang KK, Acitores Cortina JM, et al. Probing Hidden states for calibrated, alignment-resistant predictions in LLMs. 2025.","DOI":"10.1101\/2025.09.17.25336018"},{"key":"518_CR11","doi-asserted-by":"publisher","first-page":"12847","DOI":"10.18653\/v1\/2024.findings-emnlp.751","volume-title":"Findings of the association for computational linguistics: EMNLP 2024","author":"M Beigi","year":"2024","unstructured":"Beigi M, Shen Y, Yang R, Lin Z, Wang Q, Mohan A, et al. InternalInspector I2: robust confidence Estimation in LLMs through internal States. Findings of the association for computational linguistics: EMNLP 2024. Stroudsburg, PA, USA: Association for Computational Linguistics. 2024;12847\u201365."},{"key":"518_CR12","doi-asserted-by":"publisher","unstructured":"Khanmohammadi, R., Miahi, E., Mardikoraem, M., Kaur, S., Brugere, I., Smiley, C., Thind, K. S., & Ghassemi, M. M. (2025). Calibrating LLM confidence by probing perturbed representation stability. In C. Christodoulopoulos, T. Chakraborty, C. Rose, & V. Peng (Eds.), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 10448\u201310514). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2025.emnlp-main.530","DOI":"10.18653\/v1\/2025.emnlp-main.530"},{"key":"518_CR13","doi-asserted-by":"crossref","unstructured":"Ji Z, Chen D, Ishii E, Cahyawijaya S, Bang Y, Wilie B et al. LLM internal States reveal hallucination risk faced with a query. 2024 Sep 29.","DOI":"10.18653\/v1\/2024.blackboxnlp-1.6"}],"container-title":["BioData Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00518-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13040-026-00518-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13040-026-00518-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T04:29:45Z","timestamp":1770265785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13040-026-00518-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":13,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["518"],"URL":"https:\/\/doi.org\/10.1186\/s13040-026-00518-4","relation":{},"ISSN":["1756-0381"],"issn-type":[{"value":"1756-0381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]},"assertion":[{"value":"5 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10"}}