{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T12:56:55Z","timestamp":1782219415237,"version":"3.54.5"},"reference-count":51,"publisher":"Tsinghua University Press","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61533018,61402220"],"award-info":[{"award-number":["61533018,61402220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010224","name":"Philosophy and Social Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["16YBA323"],"award-info":[{"award-number":["16YBA323"]}],"id":[{"id":"10.13039\/501100010224","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Big Data Min. Anal."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.26599\/bdma.2024.9020097","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:42Z","timestamp":1770411162000},"page":"376-392","source":"Crossref","is-referenced-by-count":3,"title":["Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications"],"prefix":"10.26599","volume":"9","author":[{"given":"Long","family":"Cui","sequence":"first","affiliation":[{"name":"School of Computer, University of South China,Hengyang,China,421001"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongbin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer, University of South China,Hengyang,China,421001"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunping","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Computer, University of South China,Hengyang,China,421001"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer, University of South China,Hengyang,China,421001"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangtao","family":"Zhang","sequence":"additional","affiliation":[{"name":"The 305th Hospital of the Chinese People's Liberation Army,Beijing,China,100017"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaping","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer, University of South China,Hengyang,China,421001"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Public Health, University of South China,Hengyang,China,421001"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00195"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102596"},{"key":"ref3","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"159","article-title":"Language models are few-shot learners","volume-title":"Proc. 34th Int. Conf. Neural Information Processing Systems","author":"Brown"},{"issue":"1","key":"ref6","first-page":"240","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","article-title":"Can generalist foundation models outcompete special-purpose tuning? Case study in medicine","author":"Nori","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref10","volume-title":"OpenBioLLMs: Advancing open-source large language models for healthcare and life sciences","author":"Pal","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"ref13","article-title":"MedAlpaca \u2013 an open-source collection of medical conversational AI models and training data","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"2011","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. 36th Int. Conf. Neural Information Processing Systems","author":"Ouyang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref16","article-title":"Hallucination is inevitable: An innate limitation of large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"793","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. 34th Int. Conf. Neural Information Processing Systems","author":"Lewis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"ref19","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"A survey on RAG meets LLMs: Towards retrieval-augmented large language models","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"ref23","article-title":"Self-RAG: Learning to retrieve, generate, and critique through self-reflection","volume-title":"Proc. 12th Int. Conf. Learning Representations","author":"Asai"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.281"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.372"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00144"},{"key":"ref28","article-title":"Mods: Model-oriented data selection for instruction tuning","author":"Du","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103408"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020052"},{"key":"ref31","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learning Representations, Virtual Event","author":"Hu","year":"2021"},{"key":"ref32","volume-title":"Llama 3 Model Card","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0819"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.184"},{"key":"ref35","article-title":"LawGPT: A Chinese legal knowledge-enhanced large language model","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref38","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"2400","article-title":"LIMA: Less is more for alignment","volume-title":"Proc. 37th Int. Conf. Neural Information Processing Systems","author":"Zhou"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad651"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae238"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.165"},{"key":"ref47","article-title":"RAFT: Adapting language model to domain specific RAG","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. 36th Int. Conf. Neural Information Processing Systems","author":"Wei"},{"key":"ref49","article-title":"Data interpreter: AnLLM agent for data science","author":"Hong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1259"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02068-4"}],"container-title":["Big Data Mining and Analytics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8254253\/11373433\/11373441.pdf?arnumber=11373441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:22Z","timestamp":1770671422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.26599\/bdma.2024.9020097","relation":{},"ISSN":["2096-0654","2097-406X"],"issn-type":[{"value":"2096-0654","type":"print"},{"value":"2097-406X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}