{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:24:32Z","timestamp":1787041472235,"version":"build-2736575974"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.jbi.2026.105081","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:29:24Z","timestamp":1784042964000},"page":"105081","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Real-time hallucination detection and intervention in medical LLMs via calibrated hidden-state probes"],"prefix":"10.1016","volume":"181","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3160-0600","authenticated-orcid":false,"given":"Zhengqiu","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangrong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jbi.2026.105081_b1","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"6449","article-title":"HaluEval: A large-scale hallucination evaluation benchmark for large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.jbi.2026.105081_b2","series-title":"Proceedings of the 18th International Workshop on Semantic Evaluation","first-page":"1979","article-title":"SemEval-2024 task 6: SHROOM, a shared-task on hallucinations and related observable overgeneration mistakes","author":"Mickus","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b3","series-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"24128","article-title":"HalluLens: LLM hallucination benchmark","author":"Bang","year":"2025"},{"key":"10.1016\/j.jbi.2026.105081_b4","series-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","first-page":"2858","article-title":"MedHallu: A comprehensive benchmark for detecting medical hallucinations in large language models","author":"Pandit","year":"2025"},{"issue":"2","key":"10.1016\/j.jbi.2026.105081_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2023","journal-title":"ACM Trans. Inform. Syst."},{"key":"10.1016\/j.jbi.2026.105081_b6","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"19519","article-title":"Factuality of large language models: A survey","author":"Wang","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b7","series-title":"Findings of the Association for Computational Linguistics","first-page":"6748","article-title":"Can we trust AI doctors? A survey of medical hallucination in large language and large vision-language models","author":"Zhu","year":"2025"},{"key":"10.1016\/j.jbi.2026.105081_b8","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"9004","article-title":"SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models","author":"Manakul","year":"2023"},{"key":"10.1016\/j.jbi.2026.105081_b9","unstructured":"Lorenz Kuhn, Yarin Gal, Sebastian Farquhar, Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation, in: International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.jbi.2026.105081_b10","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"9333","article-title":"InterrogateLLM: Zero-resource hallucination detection in LLM-generated answers","author":"Yehuda","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b11","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"7744","article-title":"Mitigating hallucinations of large language models in medical information extraction via contrastive decoding","author":"Xu","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b12","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2025","first-page":"6061","article-title":"Regularized contrastive decoding with hard negative samples for LLM hallucination mitigation","author":"Sheng","year":"2025"},{"key":"10.1016\/j.jbi.2026.105081_b13","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"967","article-title":"The internal state of an LLM knows when it\u2019s lying","author":"Azaria","year":"2023"},{"key":"10.1016\/j.jbi.2026.105081_b14","unstructured":"Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt, Discovering Latent Knowledge in Language Models Without Supervision, in: International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.jbi.2026.105081_b15","series-title":"Language models (mostly) know what they know","author":"Kadavath","year":"2022"},{"key":"10.1016\/j.jbi.2026.105081_b16","series-title":"Advances in Neural Information Processing Systems 36","article-title":"Inference-time intervention: Eliciting truthful answers from a language model","author":"Li","year":"2023"},{"key":"10.1016\/j.jbi.2026.105081_b17","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, Denny Zhou, Self-Consistency Improves Chain of Thought Reasoning in Language Models, in: The Eleventh International Conference on Learning Representations, ICLR, 2023."},{"key":"10.1016\/j.jbi.2026.105081_b18","series-title":"A stitch in time saves nine: Detecting and mitigating hallucinations of LLMs by validating low-confidence generation","author":"Varshney","year":"2023"},{"key":"10.1016\/j.jbi.2026.105081_b19","series-title":"Do LLMs know about hallucination? An empirical investigation of LLM\u2019s hidden states","author":"Duan","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b20","unstructured":"Chao Chen, Kai Liu, Ze Chen, Yi Gu, Yue Wu, Mingyuan Tao, Zhihang Fu, Jieping Ye, INSIDE: LLM\u2019s Internal States Retain the Power of Hallucination Detection, in: Proc. ICLR, 2024."},{"key":"10.1016\/j.jbi.2026.105081_b21","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"14379","article-title":"Unsupervised real-time hallucination detection based on the internal states of large language models","author":"Su","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b22","series-title":"HuDEx: Integrating hallucination detection and explainability for enhancing the reliability of LLM responses","author":"Lee","year":"2025"},{"key":"10.1016\/j.jbi.2026.105081_b23","unstructured":"Zhongxiang Sun, Xiaoxue Zang, Kai Zheng, Yang Song, Jun Xu, Xiao Zhang, Weijie Yu, Han Li, ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability, in: International Conference on Learning Representations, 2025."},{"key":"10.1016\/j.jbi.2026.105081_b24","series-title":"Proceedings of the 27th Conference on Computational Natural Language Learning","first-page":"314","article-title":"Med-HALT: Medical domain hallucination test for large language models","author":"Pal","year":"2023"},{"issue":"14","key":"10.1016\/j.jbi.2026.105081_b25","doi-asserted-by":"crossref","first-page":"6421","DOI":"10.3390\/app11146421","article-title":"What disease does this patient have? A large-scale open domain question answering dataset from medical exams","volume":"11","author":"Jin","year":"2021","journal-title":"Appl. Sci."},{"key":"10.1016\/j.jbi.2026.105081_b26","unstructured":"Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, Pengcheng He, DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models, in: The Twelfth International Conference on Learning Representations, ICLR, 2024."},{"key":"10.1016\/j.jbi.2026.105081_b27","series-title":"Benchmarking retrieval-augmented generation for medicine","author":"Xiong","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b28","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (Short Papers)","first-page":"805","article-title":"Step-by-step fact verification system for medical claims with explainable reasoning","author":"Vladika","year":"2025"},{"key":"10.1016\/j.jbi.2026.105081_b29","series-title":"MedRAGChecker: Claim-level verification for biomedical retrieval-augmented generation","author":"Ji","year":"2026"},{"key":"10.1016\/j.jbi.2026.105081_b30","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics","first-page":"3076","article-title":"A probabilistic framework for LLM hallucination detection via belief tree propagation","author":"Hou","year":"2025"},{"issue":"1\/2","key":"10.1016\/j.jbi.2026.105081_b31","doi-asserted-by":"crossref","first-page":"100","DOI":"10.2307\/2333009","article-title":"Continuous inspection schemes","volume":"41","author":"Page","year":"1954","journal-title":"Biometrika"},{"issue":"3","key":"10.1016\/j.jbi.2026.105081_b32","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1080\/00401706.1959.10489860","article-title":"Control chart tests based on geometric moving averages","volume":"1","author":"Roberts","year":"1959","journal-title":"Technometrics"},{"issue":"4","key":"10.1016\/j.jbi.2026.105081_b33","doi-asserted-by":"crossref","first-page":"44:1","DOI":"10.1145\/2523813","article-title":"A survey on concept drift adaptation","volume":"46","author":"Gama","year":"2014","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.jbi.2026.105081_b34","series-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","author":"He","year":"2021"},{"key":"10.1016\/j.jbi.2026.105081_b35","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","first-page":"2567","article-title":"PubMedQA: A dataset for biomedical research question answering","author":"Jin","year":"2019"},{"key":"10.1016\/j.jbi.2026.105081_b36","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"10.1016\/j.jbi.2026.105081_b37","series-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"10.1016\/j.jbi.2026.105081_b38","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"5848","article-title":"BioMistral: A collection of open-source pretrained large language models for medical domains","author":"Labrak","year":"2024"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S153204642600105X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S153204642600105X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T07:29:09Z","timestamp":1787038149000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S153204642600105X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":38,"alternative-id":["S153204642600105X"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105081","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Real-time hallucination detection and intervention in medical LLMs via calibrated hidden-state probes","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105081","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"105081"}}