{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T17:45:13Z","timestamp":1793727913400,"version":"4.6.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":30,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100005892","name":"China Academy of Chinese Medical Sciences","doi-asserted-by":"publisher","award":["ZZ170320"],"award-info":[{"award-number":["ZZ170320"]}],"id":[{"id":"10.13039\/501100005892","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005892","name":"China Academy of Chinese Medical Sciences","doi-asserted-by":"publisher","award":["ZZ18XRZ069"],"award-info":[{"award-number":["ZZ18XRZ069"]}],"id":[{"id":"10.13039\/501100005892","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["7254504"],"award-info":[{"award-number":["7254504"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["7252253"],"award-info":[{"award-number":["7252253"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-025-06387-6","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T06:33:25Z","timestamp":1766471605000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["TCMEval-PA: a question-answering benchmark dataset for the prescription audit of Traditional Chinese Medicine"],"prefix":"10.1038","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6812-0256","authenticated-orcid":false,"given":"Baifeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2387-784X","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peixin","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyu","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8221-7574","authenticated-orcid":false,"given":"Suyuan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5592-8258","authenticated-orcid":false,"given":"Yan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"6387_CR1","doi-asserted-by":"publisher","unstructured":"Li, Y. et al. A comparative study of recent large language models on generating hospital discharge summaries for lung cancer patients. Journal of Biomedical Informatics 168104867, https:\/\/doi.org\/10.1016\/j.jbi.2025.104867 (2025)","DOI":"10.1016\/j.jbi.2025.104867"},{"key":"6387_CR2","doi-asserted-by":"publisher","unstructured":"Li, Y. et al. Improving entity recognition using ensembles of deep learning and fine-tuned large language models: A case study on adverse event extraction from VAERS and social media. Journal of Biomedical Informatics 163104789 https:\/\/doi.org\/10.1016\/j.jbi.2025.104789 (2025).","DOI":"10.1016\/j.jbi.2025.104789"},{"key":"6387_CR3","doi-asserted-by":"publisher","first-page":"721","DOI":"10.3350\/cmh.2023.0089","volume":"29","author":"YH Yeo","year":"2023","unstructured":"Yeo, Y. H. et al. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. Clin Mol Hepatol 29, 721\u2013732, https:\/\/doi.org\/10.3350\/cmh.2023.0089 (2023).","journal-title":"Clin Mol Hepatol"},{"key":"6387_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-023-02021-3","volume":"47","author":"H Song","year":"2023","unstructured":"Song, H. et al. Evaluating the Performance of Different Large Language Models on Health Consultation and Patient Education in Urolithiasis. J Med Syst 47, 125, https:\/\/doi.org\/10.1007\/s10916-023-02021-3 (2023).","journal-title":"J Med Syst"},{"key":"6387_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-06769-1","volume":"15","author":"M Motegi","year":"2025","unstructured":"Motegi, M. et al. Comparison of physician and large language model chatbot responses to online ear, nose, and throat inquiries. Sci Rep 15, 21346, https:\/\/doi.org\/10.1038\/s41598-025-06769-1 (2025).","journal-title":"Sci Rep"},{"key":"6387_CR6","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1038\/s41386-024-01841-2","volume":"49","author":"RH Perlis","year":"2024","unstructured":"Perlis, R. H., Goldberg, J. F., Ostacher, M. J. & Schneck, C. D. Clinical decision support for bipolar depression using large language models. Neuropsychopharmacology 49, 1412\u20131416, https:\/\/doi.org\/10.1038\/s41386-024-01841-2 (2024).","journal-title":"Neuropsychopharmacology"},{"key":"6387_CR7","doi-asserted-by":"publisher","first-page":"182","DOI":"10.2337\/dci24-0079","volume":"48","author":"JM Pavon","year":"2025","unstructured":"Pavon, J. M., Schlientz, D., Maciejewski, M. L., Economou-Zavlanos, N. & Lee, R. H. Large Language Models in Diabetes Management: The Need for Human and Artificial Intelligence Collaboration. Diabetes Care 48, 182\u2013184, https:\/\/doi.org\/10.2337\/dci24-0079 (2025).","journal-title":"Diabetes Care"},{"key":"6387_CR8","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1001\/jama.2023.14217","volume":"330","author":"NH Shah","year":"2023","unstructured":"Shah, N. H., Entwistle, D. & Pfeffer, M. A. Creation and Adoption of Large Language Models in Medicine. JAMA 330, 866\u2013869, https:\/\/doi.org\/10.1001\/jama.2023.14217 (2023).","journal-title":"JAMA"},{"key":"6387_CR9","doi-asserted-by":"publisher","unstructured":"Du X. et al. Performance and improvement strategies for adapting generative large language models for electronic health record applications: A systematic review. International Journal of Medical Informatics 205106091, https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.106091 (2026).","DOI":"10.1016\/j.ijmedinf.2025.106091"},{"key":"6387_CR10","unstructured":"Huang, L. et al. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. arXiv:2311.05232. https:\/\/ui.adsabs.harvard.edu\/abs\/2023arXiv231105232H (2023)."},{"key":"6387_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109887","volume":"189","author":"Y Zhuang","year":"2025","unstructured":"Zhuang, Y., Yu, L., Jiang, N. & Ge, Y. TCM-KLLaMA: Intelligent generation model for Traditional Chinese Medicine Prescriptions based on knowledge graph and large language model. Comput Biol Med 189, 109887, https:\/\/doi.org\/10.1016\/j.compbiomed.2025.109887 (2025).","journal-title":"Comput Biol Med"},{"key":"6387_CR12","doi-asserted-by":"publisher","first-page":"2792","DOI":"10.7150\/ijms.111780","volume":"22","author":"E Yu","year":"2025","unstructured":"Yu, E. et al. Large Language Models in Medicine: Applications, Challenges, and Future Directions. Int J Med Sci 22, 2792\u20132801, https:\/\/doi.org\/10.7150\/ijms.111780 (2025).","journal-title":"Int J Med Sci"},{"key":"6387_CR13","unstructured":"Kim, Y. et al. Medical Hallucinations in Foundation Models and Their Impact on Healthcare. arXiv:2503.05777. https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250305777K (2025)."},{"key":"6387_CR14","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1093\/qjmed\/hcp052","volume":"102","author":"JK Aronson","year":"2009","unstructured":"Aronson, J. K. Medication errors: what they are, how they happen, and how to avoid them. Qjm 102, 513\u2013521, https:\/\/doi.org\/10.1093\/qjmed\/hcp052 (2009).","journal-title":"Qjm"},{"key":"6387_CR15","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.jpha.2019.05.005","volume":"9","author":"YY Chen","year":"2019","unstructured":"Chen, Y. Y. et al. Elucidating the interaction of kansui and licorice by comparative plasma\/tissue metabolomics and a heatmap with relative fold change. J Pharm Anal 9, 312\u2013323, https:\/\/doi.org\/10.1016\/j.jpha.2019.05.005 (2019).","journal-title":"J Pharm Anal"},{"key":"6387_CR16","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.jep.2018.03.036","volume":"220","author":"JY Kee","year":"2018","unstructured":"Kee, J. Y., Han, Y. H., Mun, J. G., Um, J. Y. & Hong, S. H. Pharmacological effect of prohibited combination pair Panax ginseng and Veratrum nigrum on colorectal metastasis in vitro and in vivo. J Ethnopharmacol 220, 177\u2013187, https:\/\/doi.org\/10.1016\/j.jep.2018.03.036 (2018).","journal-title":"J Ethnopharmacol"},{"key":"6387_CR17","unstructured":"Yue, W. et al. TCMBench: A Comprehensive Benchmark for Evaluating Large Language Models in Traditional Chinese Medicine. arXiv:2406.01126. https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240601126Y (2024)."},{"key":"6387_CR18","unstructured":"Yu, P., Song, K., He, F., Chen, M. & Lu, J. TCMD: A Traditional Chinese Medicine QA Dataset for Evaluating Large Language Models. arXiv:2406.04941. https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240604941Y (2024)."},{"key":"6387_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-04772-9","volume":"12","author":"Z Wang","year":"2025","unstructured":"Wang, Z. et al. TCMEval-SDT: a benchmark dataset for syndrome differentiation thought of traditional Chinese medicine. Sci Data 12, 437, https:\/\/doi.org\/10.1038\/s41597-025-04772-9 (2025).","journal-title":"Sci Data"},{"key":"6387_CR20","doi-asserted-by":"publisher","first-page":"e75103","DOI":"10.2196\/75103","volume":"13","author":"C Chen","year":"2025","unstructured":"Chen, C. et al. Evaluating and Improving Syndrome Differentiation Thinking Ability in Large Language Models: Method Development Study. JMIR Med Inform 13, e75103, https:\/\/doi.org\/10.2196\/75103 (2025).","journal-title":"JMIR Med Inform"},{"key":"6387_CR21","doi-asserted-by":"publisher","unstructured":"Li, Y. et al. Relation extraction using large language models: a case study on acupuncture point locations. Journal of the American Medical Informatics Association 31(11), 2622\u20132631, https:\/\/doi.org\/10.1093\/jamia\/ocae233 (2024).","DOI":"10.1093\/jamia\/ocae233"},{"key":"6387_CR22","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.dcmed.2025.01.007","volume":"7","author":"T Haoyu","year":"2024","unstructured":"Haoyu, T. et al. TCMLLM-PR: evaluation of large language models for prescription recommendation in traditional Chinese medicine. Digital Chinese Medicine 7, 343\u2013355, https:\/\/doi.org\/10.1016\/j.dcmed.2025.01.007 (2024).","journal-title":"Digital Chinese Medicine"},{"key":"6387_CR23","unstructured":"Kong, S. et al. MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine. arXiv:2506.01252. https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250601252K (2025)."},{"key":"6387_CR24","unstructured":"Editorial Committee for \u201cNational Licensed Pharmacist Qualification Examination: Past Papers and Explanations (Traditional Chinese Pharmacy)\u201d. National Licensed Pharmacist Qualification Examination: Past Papers and Explanations \u2014 Traditional Chinese Pharmacy, 6th Edition. (China Medical Science and Technology Press, 2014)."},{"key":"6387_CR25","unstructured":"Peng, C., Ma, W. & Lu, X. Comprehensive Knowledge and Skills in Traditional Chinese Pharmacy. (China Medical Science and Technology Press, 2015)."},{"key":"6387_CR26","unstructured":"Expert Panel for the Exam Practice Workbook of the Licensed Pharmacist Qualification Examination. Exam Practice Workbook for Licensed Pharmacists (Traditional Chinese Pharmacy), 2011 Edition. (Peking Union Medical College Press, 2011)."},{"key":"6387_CR27","unstructured":"Expert Panel for the Exam Practice Workbook of the Licensed Pharmacist Qualification Examination et al. Exam Practice Workbook for Licensed Pharmacists (Traditional Chinese Pharmacy), 2010 Edition. (Peking Union Medical College Press, 2010)."},{"key":"6387_CR28","unstructured":"Niu, X. National Professional and Technical Qualification Examination: Traditional Chinese Pharmacy (Practitioner Level) \u2014 Final Sprint, 2015. (Beijing Science and Technology Press, 2015)."},{"key":"6387_CR29","unstructured":"Niu, X. National Professional and Technical Qualification Examination: Traditional Chinese Pharmacy (Technician Level) \u2014 Final Sprint, 2015. (Beijing Science and Technology Press, 2014)."},{"key":"6387_CR30","unstructured":"Niu, X. National Professional and Technical Qualification Examination: Traditional Chinese Pharmacy (Intermediate Level) \u2014 Final Sprint, 2012. (Beijing Science and Technology Press)."},{"key":"6387_CR31","doi-asserted-by":"publisher","unstructured":"Zhu, Y. TCMEval-PA. https:\/\/doi.org\/10.6084\/m9.figshare.29651261.v3 (2025).","DOI":"10.6084\/m9.figshare.29651261.v3"},{"key":"6387_CR32","unstructured":"OpenAI et al. GPT-4o System Card. arXiv:2410.21276. https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv241021276O (2024)."},{"key":"6387_CR33","unstructured":"DeepSeek-AI et al. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948. https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250112948D (2025)."},{"key":"6387_CR34","unstructured":"Bai, J. et al. Qwen Technical Report. arXiv:2309.16609. https:\/\/ui.adsabs.harvard.edu\/abs\/2023arXiv230916609B (2023)."},{"key":"6387_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H. et al. HuatuoGPT, towards Taming Language Model to Be a Doctor. arXiv:2305.15075. https:\/\/ui.adsabs.harvard.edu\/abs\/2023arXiv230515075Z (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"6387_CR36","unstructured":"Zhu, W. W. & Wang, X. Shennong-tcm: A traditional chinese medicine large language model. GitHub (2023)."},{"key":"6387_CR37","doi-asserted-by":"crossref","unstructured":"Pandit, S. et al. MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models. arXiv:2502.14302. https:\/\/ui.adsabs.harvard.edu\/abs\/2025arXiv250214302P (2025).","DOI":"10.18653\/v1\/2025.emnlp-main.143"},{"key":"6387_CR38","unstructured":"Ma, M. D. et al. CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making. arXiv:2406.09923. https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240609923M (2024)."},{"key":"6387_CR39","unstructured":"Phan Van, P., Nguyen Minh, D., Dinh Ngoc, A. & Phan Thanh, H. Rx Strategist: Prescription Verification using LLM Agents System. arXiv:2409.03440. https:\/\/ui.adsabs.harvard.edu\/abs\/2024arXiv240903440P (2024)."}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06387-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06387-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06387-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T00:06:36Z","timestamp":1769213196000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-025-06387-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["6387"],"URL":"https:\/\/doi.org\/10.1038\/s41597-025-06387-6","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,23]]},"assertion":[{"value":"4 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"79"}}