{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:50:28Z","timestamp":1776250228804,"version":"3.50.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"vor","delay-in-days":40,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100016808","name":"Natural Science Foundation of Xiamen Municipality","doi-asserted-by":"publisher","award":["3502Z202471035"],"award-info":[{"award-number":["3502Z202471035"]}],"id":[{"id":"10.13039\/100016808","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024HQYJ01"],"award-info":[{"award-number":["2024HQYJ01"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-34835-1","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:07:00Z","timestamp":1772813220000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-based medical dialogue dataset generation with automated instructions"],"prefix":"10.1038","volume":"16","author":[{"given":"Hao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanlang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyu","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"34835_CR1","doi-asserted-by":"crossref","unstructured":"Zeng, G. et al. MedDialog: Large-scale medical dialogue datasets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 9241\u20139250 (Online, 2020).","DOI":"10.18653\/v1\/2020.emnlp-main.743"},{"key":"34835_CR2","doi-asserted-by":"crossref","unstructured":"Joshi, A. et al. Dr. summarize: Global summarization of medical dialogue by exploiting local structures. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 3755\u20133763 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.335"},{"key":"34835_CR3","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med.30, 2613\u20132622 (2024).","journal-title":"Nat. Med."},{"key":"34835_CR4","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.21037\/qims-23-892","volume":"14","author":"D Tian","year":"2024","unstructured":"Tian, D. et al. The role of large language models in medical image processing: A narrative review. Quant. Imaging Med. Surg.14, 1108\u20131121 (2024).","journal-title":"Quant. Imaging Med. Surg."},{"key":"34835_CR5","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","volume":"5","author":"X Yang","year":"2022","unstructured":"Yang, X. et al. A large language model for electronic health records. NPJ Digital Med.5, 194 (2022).","journal-title":"NPJ Digital Med."},{"key":"34835_CR6","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1111\/medu.15402","volume":"58","author":"HC Lucas","year":"2024","unstructured":"Lucas, H. C., Upperman, J. S. & Robinson, J. R. A systematic review of large language models and their implications in medical education. Med. Educ.58, 1276\u20131285 (2024).","journal-title":"Med. Educ."},{"key":"34835_CR7","doi-asserted-by":"crossref","unstructured":"Kumichev, G. et al. Medsyn: Llm-based synthetic medical text generation framework. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 215\u2013230 (Springer, 2024).","DOI":"10.1007\/978-3-031-70381-2_14"},{"key":"34835_CR8","first-page":"29319","volume":"39","author":"Y Zhong","year":"2025","unstructured":"Zhong, Y. Advancing medical multimodal learning and data generation with diffusion model and llm. Proc. AAAI Conf. Artif. Intell.39, 29319\u201329320 (2025).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"34835_CR9","unstructured":"Lu, K. et al. #instag: Instruction tagging for analyzing supervised fine-tuning of large language models. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following (2023)."},{"key":"34835_CR10","doi-asserted-by":"crossref","unstructured":"Bach, S. et al. Promptsource: An integrated development environment and repository for natural language prompts. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 93\u2013104 (Dublin, Ireland, 2022).","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"34835_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Y. et al. Super-naturalinstructions: Generalization via declarative instructions on 1600+ NLP tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 5085\u20135109 (Abu Dhabi, United Arab Emirates, 2022).","DOI":"10.18653\/v1\/2022.emnlp-main.340"},{"key":"34835_CR12","doi-asserted-by":"crossref","unstructured":"Honovich, O. et al. Unnatural instructions: Tuning language models with (almost) no human labor. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 14409\u201314428 (Toronto, Canada, 2023).","DOI":"10.18653\/v1\/2023.acl-long.806"},{"key":"34835_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Y. et al. Self-instruct: Aligning language models with self-generated instructions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 13484\u201313508 (Toronto, Canada, 2023).","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"34835_CR14","doi-asserted-by":"crossref","unstructured":"Sun, Z. et al. Principle-driven self-alignment of language models from scratch with minimal human supervision. In Advances in Neural Information Processing Systems, 2511\u20132565 (2023).","DOI":"10.52202\/075280-0115"},{"key":"34835_CR15","unstructured":"Li, D. et al. Llm-ddi: Leveraging large language models for drug-drug interaction prediction on biomedical knowledge graph. IEEE Journal of Biomedical and Health Informatics (Early Access) ."},{"key":"34835_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, L., Qiao, S., Zhou, Z. & Chen, J. Intelligent medical consultation system based on the gpt model. In Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering, 1192\u20131197 (2023).","DOI":"10.1145\/3650400.3650601"},{"key":"34835_CR17","doi-asserted-by":"crossref","unstructured":"Fawzi, S. A review of the role of chatgpt for clinical decision support systems. In 2023 5th Novel Intelligent and Leading Emerging Sciences Conference (NILES), 439\u2013442 (IEEE, 2023).","DOI":"10.1109\/NILES59815.2023.10296668"},{"key":"34835_CR18","doi-asserted-by":"crossref","unstructured":"Karak, A. & Kunal, K. Implementation of gpt models for text generation in healthcare domain. In 2023 International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS), 1, 1\u20136 (IEEE, 2023).","DOI":"10.1109\/ICCAMS60113.2023.10525972"},{"key":"34835_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y. et al. Chatdoctor: A medical chat model fine-tuned on LLaMA model using medical domain knowledge (2023). arXiv:2303.14070.","DOI":"10.7759\/cureus.40895"},{"key":"34835_CR20","unstructured":"Das, T., Albassam, D. & Sun, J. Synthetic patient-physician dialogue generation from clinical notes using llm (2024). arXiv:2408.06285."},{"key":"34835_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H. et al. LogiCoT: Logical chain-of-thought instruction-tuning data collection with GPT-4. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2908\u20132921 (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.191"},{"key":"34835_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. Meddg: An entity-centric medical consultation dataset for entity-aware medical dialogue generation. In CCF International Conference on Natural Language Processing and Chinese Computing, 447\u2013459 (Springer, 2022).","DOI":"10.1007\/978-3-031-17120-8_35"},{"key":"34835_CR23","unstructured":"Bao, Z. et al. Disc-medllm: Bridging general large language models and real-world medical consultation (2023). arXiv:2308.14346."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34835-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34835-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34835-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T09:57:41Z","timestamp":1776247061000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34835-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["34835"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-34835-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"assertion":[{"value":"6 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12410"}}