{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T06:55:39Z","timestamp":1791442539490,"version":"4.3.3"},"reference-count":68,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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","award":["62577049"],"award-info":[{"award-number":["62577049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence in Medicine"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.artmed.2026.103540","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T15:25:46Z","timestamp":1789745146000},"page":"103540","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CReaTe-LM: A large language model for stepwise, heuristic clinical reasoning instruction"],"prefix":"10.1016","volume":"182","author":[{"given":"Zhengqi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4786-0611","authenticated-orcid":false,"given":"Shuang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8147-5257","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyuan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1566-9343","authenticated-orcid":false,"given":"Fuli","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5863-8283","authenticated-orcid":false,"given":"Haigen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengyi","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.artmed.2026.103540_b1","doi-asserted-by":"crossref","first-page":"3399","DOI":"10.1038\/s41591-024-03315-w","article-title":"Systems education can train the next generation of scientists and clinicians","volume":"30","author":"Hegyi","year":"2024","journal-title":"Nat Med"},{"issue":"12","key":"10.1016\/j.artmed.2026.103540_b2","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1080\/0142159X.2024.2412796","article-title":"Implementing an accelerated three-year MD curriculum at NYU Grossman School of Medicine","volume":"46","author":"Cangiarella","year":"2024","journal-title":"Med Teach"},{"issue":"1","key":"10.1016\/j.artmed.2026.103540_b3","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s12909-024-06613-6","article-title":"Developing clinical reasoning along the cognitive continuum: a mixed methods evaluation of a novel Clinical Diagnosis Assessment","volume":"25","author":"Ainge","year":"2025","journal-title":"BMC Med Educ"},{"issue":"8","key":"10.1016\/j.artmed.2026.103540_b4","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1097\/ACM.0000000000003027","article-title":"Clinical reasoning as a core competency","volume":"95","author":"Connor","year":"2020","journal-title":"Acad Med"},{"issue":"2","key":"10.1016\/j.artmed.2026.103540_b5","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1136\/bmjqs-2021-014130","article-title":"Burden of serious harms from diagnostic error in the USA","volume":"33","author":"Newman-Toker","year":"2024","journal-title":"BMJ Qual Saf"},{"issue":"2","key":"10.1016\/j.artmed.2026.103540_b6","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1001\/jamainternmed.2023.7347","article-title":"Diagnostic errors in hospitalized adults who died or were transferred to intensive care","volume":"184","author":"Auerbach","year":"2024","journal-title":"JAMA Intern Med"},{"issue":"4","key":"10.1016\/j.artmed.2026.103540_b7","first-page":"419","article-title":"A five-step \u201cmicroskills\u201d model of clinical teaching","volume":"5","author":"Neher","year":"1992","journal-title":"J Am Board Fam Pract"},{"issue":"2","key":"10.1016\/j.artmed.2026.103540_b8","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1097\/00001888-200002000-00020","article-title":"Scripts and medical diagnostic knowledge: theory and applications for clinical reasoning instruction and research","volume":"75","author":"Charlin","year":"2000","journal-title":"Acad Med"},{"issue":"9","key":"10.1016\/j.artmed.2026.103540_b9","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1046\/j.1525-1497.2001.016009620.x","article-title":"Teaching the one-minute preceptor: a randomized controlled trial","volume":"16","author":"Furney","year":"2001","journal-title":"J Gen Intern Med"},{"issue":"9","key":"10.1016\/j.artmed.2026.103540_b10","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1097\/00001888-200309000-00010","article-title":"SNAPPS: a learner-centered model for outpatient education","volume":"78","author":"Wolpaw","year":"2003","journal-title":"Acad Med"},{"key":"10.1016\/j.artmed.2026.103540_b11","series-title":"Huatuogpt-o1, towards medical complex reasoning with llms","author":"Chen","year":"2024"},{"key":"10.1016\/j.artmed.2026.103540_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125712","article-title":"Integrated fuzzy decision-making methodology with intuitionistic fuzzy numbers: An application for disaster preparedness in clinical laboratories","volume":"263","author":"Ortiz-Barrios","year":"2025","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.artmed.2026.103540_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126138","article-title":"MEDSQ: Towards personalized medical education via multi-form interaction guidance","volume":"267","author":"Ouyang","year":"2025","journal-title":"Expert Syst Appl"},{"issue":"3","key":"10.1016\/j.artmed.2026.103540_b14","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nat Med"},{"issue":"4","key":"10.1016\/j.artmed.2026.103540_b15","doi-asserted-by":"crossref","first-page":"78","DOI":"10.5688\/ajpe81478","article-title":"Strategies for improving learner metacognition in health professional education","volume":"81","author":"Medina","year":"2017","journal-title":"Am J Pharm Educ"},{"issue":"9","key":"10.1016\/j.artmed.2026.103540_b16","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1111\/medu.15397","article-title":"When I say \u2026Socratic questioning","volume":"58","author":"Ng","year":"2024","journal-title":"Med Educ"},{"key":"10.1016\/j.artmed.2026.103540_b17","doi-asserted-by":"crossref","unstructured":"Yang S, Zhao H, Zhu S, Zhou G, Xu H, Jia Y, Zan H. Zhongjing: Enhancing the chinese medical capabilities of large language model through expert feedback and real-world multi-turn dialogue. In: Proceedings of the AAAI conference on artificial intelligence. 2024, p. 19368\u201376.","DOI":"10.1609\/aaai.v38i17.29907"},{"key":"10.1016\/j.artmed.2026.103540_b18","first-page":"1","article-title":"Knowledge-tuning large language models with structured medical knowledge bases for trustworthy response generation in Chinese","volume":"19","author":"Wang","year":"2025","journal-title":"ACM Trans Knowl Discov Data"},{"key":"10.1016\/j.artmed.2026.103540_b19","series-title":"Advances in neural information processing systems","first-page":"138632","article-title":"PediatricsGPT: Large language models as Chinese medical assistants for pediatric applications","volume":"vol. 37","author":"Yang","year":"2024"},{"issue":"21","key":"10.1016\/j.artmed.2026.103540_b20","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1056\/NEJMra054782","article-title":"Educational strategies to promote clinical diagnostic reasoning","volume":"355","author":"Bowen","year":"2006","journal-title":"N Engl J Med"},{"issue":"7","key":"10.1016\/j.artmed.2026.103540_b21","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1016\/S0277-9536(00)00098-8","article-title":"Patient-centredness: a conceptual framework and review of the empirical literature","volume":"51","author":"Mead","year":"2000","journal-title":"Soc Sci Med"},{"issue":"5","key":"10.1016\/j.artmed.2026.103540_b22","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1111\/j.1365-2923.2008.03030.x","article-title":"Effects of reflective practice on the accuracy of medical diagnoses","volume":"42","author":"Mamede","year":"2008","journal-title":"Med Educ"},{"key":"10.1016\/j.artmed.2026.103540_b23","doi-asserted-by":"crossref","first-page":"53728","DOI":"10.52202\/075280-2338","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"issue":"8","key":"10.1016\/j.artmed.2026.103540_b24","doi-asserted-by":"crossref","first-page":"958","DOI":"10.1097\/ACM.0000000000005197","article-title":"Clinical reasoning curricula in preclinical undergraduate medical education: a scoping review","volume":"98","author":"Hawks","year":"2023","journal-title":"Acad Med"},{"issue":"1","key":"10.1016\/j.artmed.2026.103540_b25","doi-asserted-by":"crossref","first-page":"1391","DOI":"10.1186\/s12909-024-06399-7","article-title":"Large language models improve clinical decision making of medical students through patient simulation and structured feedback: a randomized controlled trial","volume":"24","author":"Br\u00fcgge","year":"2024","journal-title":"BMC Med Educ"},{"issue":"1","key":"10.1016\/j.artmed.2026.103540_b26","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1038\/s41746-025-01550-0","article-title":"Enhancing diagnostic capability with multi-agents conversational large language models","volume":"8","author":"Chen","year":"2025","journal-title":"Npj Digit Med"},{"issue":"10","key":"10.1016\/j.artmed.2026.103540_b27","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.40969","article-title":"Large language model influence on diagnostic reasoning: a randomized clinical trial","volume":"7","author":"Goh","year":"2024","journal-title":"JAMA Netw Open"},{"issue":"9","key":"10.1016\/j.artmed.2026.103540_b28","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making","volume":"30","author":"Hager","year":"2024","journal-title":"Nat Med"},{"key":"10.1016\/j.artmed.2026.103540_b29","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","article-title":"A pathology foundation model for cancer diagnosis and prognosis prediction","volume":"634","author":"Wang","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.artmed.2026.103540_b30","doi-asserted-by":"crossref","first-page":"3129","DOI":"10.1038\/s41591-024-03185-2","article-title":"A generalist vision\u2013language foundation model for diverse biomedical tasks","volume":"30","author":"Zhang","year":"2024","journal-title":"Nat Med"},{"key":"10.1016\/j.artmed.2026.103540_b31","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-024-01339-7","article-title":"A multimodal multidomain multilingual medical foundation model for zero shot clinical diagnosis","volume":"8","author":"Liu","year":"2025","journal-title":"Npj Digit Med"},{"key":"10.1016\/j.artmed.2026.103540_b32","series-title":"Findings of the association for computational linguistics: ACL 2025","first-page":"24898","article-title":"MAGI: Multi-Agent guided interview for psychiatric assessment","author":"Bi","year":"2025"},{"key":"10.1016\/j.artmed.2026.103540_b33","series-title":"Findings of the association for computational linguistics: ACL 2025","first-page":"14345","article-title":"CoD, towards an interpretable medical agent using chain of diagnosis","author":"Chen","year":"2025"},{"key":"10.1016\/j.artmed.2026.103540_b34","series-title":"MedGemma technical report","author":"Sellergren","year":"2025"},{"issue":"2","key":"10.1016\/j.artmed.2026.103540_b35","doi-asserted-by":"crossref","first-page":"180","DOI":"10.3758\/BF03195563","article-title":"AutoTutor: A tutor with dialogue in natural language","volume":"36","author":"Graesser","year":"2004","journal-title":"Behav Res Methods Instrum Comput"},{"issue":"4","key":"10.1016\/j.artmed.2026.103540_b36","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/TE.2005.856149","article-title":"AutoTutor: An intelligent tutoring system with mixed-initiative dialogue","volume":"48","author":"Graesser","year":"2005","journal-title":"IEEE Trans Educ"},{"key":"10.1016\/j.artmed.2026.103540_b37","series-title":"International conference on intelligent tutoring systems","first-page":"158","article-title":"The architecture of Why2-Atlas: A coach for qualitative physics essay writing","author":"VanLehn","year":"2002"},{"key":"10.1016\/j.artmed.2026.103540_b38","doi-asserted-by":"crossref","unstructured":"Evens M, Chang R-C, Lee YH, Shim LS, Woo CW, Zbang Y. CIRCSIM-Tutor: An intelligent tutoring system using natural language dialogue. In: Fifth conference on applied natural language processing: descriptions of system demonstrations and videos. 1997, p. 13\u20134.","DOI":"10.3115\/974281.974289"},{"issue":"1","key":"10.1016\/j.artmed.2026.103540_b39","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.artmed.2005.10.004","article-title":"An intelligent tutoring system that generates a natural language dialogue using dynamic multi-level planning","volume":"38","author":"Woo","year":"2006","journal-title":"Artif Intell Med"},{"key":"10.1016\/j.artmed.2026.103540_b40","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1038\/s42256-024-00832-8","article-title":"Augmenting large language models with chemistry tools","volume":"6","author":"M. Bran","year":"2024","journal-title":"Nat Mach Intell"},{"key":"10.1016\/j.artmed.2026.103540_b41","doi-asserted-by":"crossref","unstructured":"Kazemitabaar M, Ye R, Wang X, Henley AZ, Denny P, Craig M, Grossman T. Codeaid: Evaluating a classroom deployment of an llm-based programming assistant that balances student and educator needs. In: Proceedings of the 2024 chi conference on human factors in computing systems. 2024, p. 1\u201320.","DOI":"10.1145\/3613904.3642773"},{"key":"10.1016\/j.artmed.2026.103540_b42","series-title":"Findings of the association for computational linguistics: ACL 2025","first-page":"6363","article-title":"EssayJudge: A multi-granular benchmark for assessing automated essay scoring capabilities of multimodal large language models","author":"Su","year":"2025"},{"issue":"1","key":"10.1016\/j.artmed.2026.103540_b43","first-page":"1","article-title":"PharmaSimText: A text-based educational playground filled with RL-LLM agents that work together even in disagreement","volume":"17","author":"Radmehr","year":"2025","journal-title":"J Educ Data Min"},{"key":"10.1016\/j.artmed.2026.103540_b44","doi-asserted-by":"crossref","unstructured":"Wang A, Ruparel R, Iurchenko A, Jhun P, S\u00e9guin JA, Strachan P, Wong R, Karthikesalingam A, Matias Y, Hassidim A, et al. Generative AI for medical education: Insights from a case study with medical students and an AI tutor for clinical reasoning. In: Proceedings of the extended abstracts of the CHI conference on human factors in computing systems. 2025, p. 1\u20138.","DOI":"10.1145\/3706599.3721208"},{"key":"10.1016\/j.artmed.2026.103540_b45","series-title":"Advances in neural information processing systems","first-page":"85693","article-title":"SocraticLM: Exploring socratic personalized teaching with large language models","author":"Liu","year":"2024"},{"issue":"4","key":"10.1016\/j.artmed.2026.103540_b46","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1111\/j.1365-2929.2005.02127.x","article-title":"Research in clinical reasoning: past history and current trends","volume":"39","author":"Norman","year":"2005","journal-title":"Med Educ"},{"key":"10.1016\/j.artmed.2026.103540_b47","doi-asserted-by":"crossref","unstructured":"Elkins S, Kochmar E, Cheung JC, Serban I. How teachers can use large language models and bloom\u2019s taxonomy to create educational quizzes. In: Proceedings of the AAAI conference on artificial intelligence. 2024, p. 23084\u201391.","DOI":"10.1609\/aaai.v38i21.30353"},{"key":"10.1016\/j.artmed.2026.103540_b48","series-title":"Evaluating the quality of learning: The SOLO taxonomy (structure of the observed learning outcome)","author":"Biggs","year":"1982"},{"issue":"3","key":"10.1016\/j.artmed.2026.103540_b49","doi-asserted-by":"crossref","first-page":"227","DOI":"10.3233\/IRG-2006-16(3)02","article-title":"The behavior of tutoring systems","volume":"16","author":"VanLehn","year":"2006","journal-title":"Int J Artif Intell Educ"},{"key":"10.1016\/j.artmed.2026.103540_b50","series-title":"Advances in neural information processing systems","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"vol. 35","author":"Ouyang","year":"2022"},{"key":"10.1016\/j.artmed.2026.103540_b51","doi-asserted-by":"crossref","unstructured":"Teng Z, Song Y, Ye X, Ouyang Y. Fine-tuning LLMs for multi-turn dialogues: optimizing cross-entropy loss with KL divergence for all rounds of responses. In: Proceedings of the 2024 16th international conference on machine learning and computing. 2024, p. 128\u201333.","DOI":"10.1145\/3651671.3651702"},{"key":"10.1016\/j.artmed.2026.103540_b52","doi-asserted-by":"crossref","unstructured":"Cohn C, Hutchins N, Le T, Biswas G. A chain-of-thought prompting approach with llms for evaluating students\u2019 formative assessment responses in science. In: Proceedings of the AAAI conference on artificial intelligence. 2024, p. 23182\u201390.","DOI":"10.1609\/aaai.v38i21.30364"},{"key":"10.1016\/j.artmed.2026.103540_b53","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TLT.2025.3564177","article-title":"Is ChatGPT a competent teacher? Systematic evaluation of large language models on the competency model","volume":"18","author":"Gong","year":"2025","journal-title":"IEEE Trans Learn Technol"},{"key":"10.1016\/j.artmed.2026.103540_b54","doi-asserted-by":"crossref","unstructured":"Shi Y, Liang R, Xu Y. EducationQ: Evaluating LLMs\u2019 Teaching Capabilities Through Multi-Agent Dialogue Framework. In: Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 1: long papers). 2025, p. 32799\u2013828.","DOI":"10.18653\/v1\/2025.acl-long.1576"},{"key":"10.1016\/j.artmed.2026.103540_b55","series-title":"Text summarization branches out","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.artmed.2026.103540_b56","series-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019"},{"key":"10.1016\/j.artmed.2026.103540_b57","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"10.1016\/j.artmed.2026.103540_b58","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W. LoRA: Low-Rank Adaptation of Large Language Models. In: International conference on learning representations. 2022."},{"key":"10.1016\/j.artmed.2026.103540_b59","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.artmed.2026.103540_b60","series-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025"},{"key":"10.1016\/j.artmed.2026.103540_b61","series-title":"Baichuan-m1: Pushing the medical capability of large language models","author":"Wang","year":"2025"},{"key":"10.1016\/j.artmed.2026.103540_b62","doi-asserted-by":"crossref","unstructured":"Dan Y, Lei Z, Gu Y, Li Y, Yin J, Lin J, Ye L, Tie Z, Zhou Y, Wang Y, et al. EduChat: A Large Language Model-Based Conversational Agent for Intelligent Education. In: China conference on knowledge graph and semantic computing. 2024, p. 297\u2013308.","DOI":"10.1007\/978-981-96-1809-5_22"},{"issue":"10","key":"10.1016\/j.artmed.2026.103540_b63","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1038\/s41562-024-02004-5","article-title":"Promises and challenges of generative artificial intelligence for human learning","volume":"8","author":"Yan","year":"2024","journal-title":"Nat Hum Behav"},{"key":"10.1016\/j.artmed.2026.103540_b64","doi-asserted-by":"crossref","unstructured":"Thomas DR, Lin J, Gatz E, Gurung A, Gupta S, Norberg K, Fancsali SE, Aleven V, Branstetter L, Brunskill E, et al. Improving student learning with hybrid human-AI tutoring: A three-study quasi-experimental investigation. In: Proceedings of the 14th learning analytics and knowledge conference. 2024, p. 404\u201315.","DOI":"10.1145\/3636555.3636896"},{"key":"10.1016\/j.artmed.2026.103540_b65","series-title":"Findings of the association for computational linguistics: EMNLP 2024","first-page":"13641","article-title":"Pedagogical alignment of large language models","author":"Sonkar","year":"2024"},{"key":"10.1016\/j.artmed.2026.103540_b66","series-title":"MedTutor-R1: Socratic personalized medical teaching with Multi-Agent simulation","author":"He","year":"2025"},{"key":"10.1016\/j.artmed.2026.103540_b67","unstructured":"Li Q, Cui L, Kong L, Bi W. Exploring the reliability of large language models as customized evaluators for diverse NLP tasks. In: Proceedings of the 31st international conference on computational linguistics. 2025, p. 10325\u201344."},{"key":"10.1016\/j.artmed.2026.103540_b68","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102938","article-title":"Medexpqa: Multilingual benchmarking of large language models for medical question answering","volume":"155","author":"Alonso","year":"2024","journal-title":"Artif Intell Med"}],"container-title":["Artificial Intelligence in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365726001922?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0933365726001922?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T06:47:03Z","timestamp":1791442023000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0933365726001922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":68,"alternative-id":["S0933365726001922"],"URL":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103540","relation":{},"ISSN":["0933-3657"],"issn-type":[{"value":"0933-3657","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CReaTe-LM: A large language model for stepwise, heuristic clinical reasoning instruction","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence in Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artmed.2026.103540","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103540"}}