{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:29:17Z","timestamp":1783823357842,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tetci.2024.3502465","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T15:15:01Z","timestamp":1736867701000},"page":"3057-3071","source":"Crossref","is-referenced-by-count":9,"title":["Benchmarking Medical LLMs on Anesthesiology: A Comprehensive Dataset in Chinese"],"prefix":"10.1109","volume":"9","author":[{"given":"Bohao","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Control Science and Engineering, China University of Petroleum East China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3180-0484","authenticated-orcid":false,"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhonghai","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, China University of Petroleum East China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0761-7893","authenticated-orcid":false,"given":"Baosheng","family":"Yu","sequence":"additional","affiliation":[{"name":"The University of Sydney, Darlington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8976-2084","authenticated-orcid":false,"given":"Liang","family":"Ding","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Jin","sequence":"additional","affiliation":[{"name":"First People's Hospital of Yunnan Province, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5388-9080","authenticated-orcid":false,"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, China University of Petroleum East China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0045-8724","authenticated-orcid":false,"given":"Xiongbin","family":"Wang","sequence":"additional","affiliation":[{"name":"Second Affiliated Hospital of Kunming Medical University, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0783-5273","authenticated-orcid":false,"given":"Dapeng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/educsci13040410"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4294197"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.lanwpc.2021.100166"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-051934"},{"key":"ref7","article-title":"Clinical knowledge and reasoning abilities of ai large language models in anesthesiology: A comparative study on the ABA exam","author":"Angel","year":"2023","journal-title":"medRxiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.bja.2023.04.017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00540-023-03275-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5554\/22562087.e1092"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"},{"key":"ref12","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref14","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref15","article-title":"Internlm: A multilingual language model with progressively enhanced capabilities","author":"Team","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"ref17","article-title":"Bianque: Balancing the questioning and suggestion ability of health LLMS with multi-turn health conversations polished by chatgpt","author":"Chen","year":"2023"},{"key":"ref18","article-title":"Huatuo: Tuning llama model with chinese medical knowledge","author":"Wang","year":"2023"},{"key":"ref19","article-title":"Openmedlab: An open-source platform for multi-modality foundation models in medicine","author":"Wang","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref22","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text summarization branches out","author":"Lin","year":"2004"},{"key":"ref23","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref24","volume-title":"Statistical Methods for Speech Recognition","author":"Jelinek","year":"1998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075249"},{"key":"ref26","first-page":"1137","article-title":"A neural probabilistic language model","volume-title":"J. Mach. Learn. Representations","volume":"3","author":"Bengio","year":"2003"},{"key":"ref27","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2838931.2838936"},{"key":"ref29","article-title":"Bag of tricks for effective language model pretraining and downstream adaptation: A case study on glue","author":"Zhong","year":"2023"},{"key":"ref30","article-title":"Toward efficient language model pretraining and downstream adaptation via self-evolution: A case study on superglue","author":"Zhong","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3372442"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref33","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"issue":"8","key":"ref34","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref36","first-page":"3261","article-title":"Superglue: A stickier benchmark for general-purpose language understanding systems","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref37","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref38","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref39","article-title":"Healthcare copilot: Eliciting the power of general LLMS for medical consultation","author":"Ren","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.373"},{"key":"ref41","article-title":"Can ChatGPT understand too? A comparative study on chatgpt and fine-tuned bert","author":"Zhong","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.520"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3209394"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.3040444"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3369478"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3301774"},{"key":"ref47","article-title":"Can large language models reason about medical questions?","volume":"abs\/2207.08143","author":"Livin","year":"2022","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2023.0254"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615285"},{"key":"ref50","first-page":"1","article-title":"Benchmarking large language models on cmexam-A comprehensive Chinese medical exam dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.343"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29723"},{"key":"ref53","article-title":"Radiology-llama2: Best-in-class large language model for radiology","author":"Liu","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000341"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1053\/j.jvca.2024.01.032"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/11095270\/10840322.pdf?arnumber=10840322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:05:59Z","timestamp":1764183959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10840322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":55,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3502465","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}