{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T22:17:50Z","timestamp":1769552270699,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["No.2023YFC3402800)"],"award-info":[{"award-number":["No.2023YFC3402800)"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ational Natural331 Science Foundation of China","award":["(Nos. 82441028, 82441029, 62171230, 82302352)"],"award-info":[{"award-number":["(Nos. 82441028, 82441029, 62171230, 82302352)"]}]},{"name":"iangsu Provincial Department of332 Science and Technology\u2019s major project on frontier-leading basic research in technolog","award":["(No.BK2023200"],"award-info":[{"award-number":["(No.BK2023200"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-08182-x","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:14:08Z","timestamp":1769505248000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adapting LLMs for biomedical natural language processing: a comprehensive benchmark study on fine-tuning methods"],"prefix":"10.1007","volume":"82","author":[{"given":"Junjie","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Jin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shen","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yiyan","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Yongming","family":"Miao","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,27]]},"reference":[{"issue":"4","key":"8182_CR1","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1038\/s41591-024-02843-9","volume":"30","author":"NJ Mekkes","year":"2024","unstructured":"Mekkes NJ et al (2024) Identification of clinical disease trajectories in neurodegenerative disorders with natural language processing. Nat Med 30(4):1143\u20131153","journal-title":"Nat Med"},{"key":"8182_CR2","doi-asserted-by":"crossref","unstructured":"Peng Y, Yan S, Lu Z (2019) Transfer learning in biomedical natural language processing: an evaluation of BERT and ELMo on ten benchmarking datasets. In: Proceedings of the 18th BioNLP Workshop and Shared Task, pp\u00a058\u201365","DOI":"10.18653\/v1\/W19-5006"},{"key":"8182_CR3","doi-asserted-by":"crossref","unstructured":"Alsentzer E et al (2019) Publicly available clinical BERT embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp\u00a072\u201378","DOI":"10.18653\/v1\/W19-1909"},{"issue":"8","key":"8182_CR4","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ et al (2023) Large language models in medicine. Nat Med 29(8):1930\u20131940","journal-title":"Nat Med"},{"key":"8182_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"8182_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2024.3415959","volume":"1","author":"D Wu","year":"2024","unstructured":"Wu D et al (2024) A LLM-based hybrid-transformer diagnosis system in healthcare. IEEE J Biomed Health Inform 1:1","journal-title":"IEEE J Biomed Health Inform"},{"key":"8182_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107437","volume":"103","author":"A AlShibli","year":"2025","unstructured":"AlShibli A et al (2025) Vision-BioLLM: large vision language model for visual dialogue in biomedical imagery. Biomed Signal Process Control 103:107437","journal-title":"Biomed Signal Process Control"},{"issue":"1","key":"8182_CR8","doi-asserted-by":"publisher","first-page":"AIcs2400360","DOI":"10.1056\/AIcs2400360","volume":"2","author":"M Wornow","year":"2025","unstructured":"Wornow M et al (2025) Zero-shot clinical trial patient matching with LLMS. NEJM AI 2(1):AIcs2400360","journal-title":"NEJM AI"},{"issue":"4","key":"8182_CR9","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/j.surg.2023.12.014","volume":"175","author":"BR Beaulieu-Jones","year":"2024","unstructured":"Beaulieu-Jones BR et al (2024) Evaluating capabilities of large language models: performance of GPT-4 on surgical knowledge assessments. Surgery 175(4):936\u2013942","journal-title":"Surgery"},{"issue":"1","key":"8182_CR10","doi-asserted-by":"publisher","first-page":"e35","DOI":"10.1016\/S2589-7500(24)00246-2","volume":"7","author":"MCS Menezes","year":"2025","unstructured":"Menezes MCS et al (2025) The potential of generative pre-trained transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study. Lancet Dig Health 7(1):e35\u2013e43","journal-title":"Lancet Dig Health"},{"issue":"6","key":"8182_CR11","doi-asserted-by":"publisher","first-page":"e333","DOI":"10.1016\/S2589-7500(23)00083-3","volume":"5","author":"H Li","year":"2023","unstructured":"Li H et al (2023) Ethics of large language models in medicine and medical research. Lancet Dig Health 5(6):e333\u2013e335","journal-title":"Lancet Dig Health"},{"key":"8182_CR12","doi-asserted-by":"publisher","DOI":"10.2196\/60501","volume":"26","author":"J Zaghir","year":"2024","unstructured":"Zaghir J et al (2024) Prompt engineering paradigms for medical applications: scoping review. J Med Internet Res 26:e60501","journal-title":"J Med Internet Res"},{"issue":"4","key":"8182_CR13","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J et al (2020) BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4):1234\u20131240","journal-title":"Bioinformatics"},{"key":"8182_CR14","doi-asserted-by":"crossref","unstructured":"Liu X et al (2021) P-tuning v2: prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602","DOI":"10.18653\/v1\/2022.acl-short.8"},{"issue":"140","key":"8182_CR15","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C et al (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21(140):1\u201367","journal-title":"J Mach Learn Res"},{"key":"8182_CR16","doi-asserted-by":"crossref","unstructured":"Wang L et al (2024) Parameter-efficient fine-tuning in large models: a survey of methodologies. arXiv preprint arXiv:2410.19878","DOI":"10.21203\/rs.3.rs-5393239\/v1"},{"key":"8182_CR17","unstructured":"Hu EJ et al (2022) LoRA: low-rank adaptation of large language models. In: International conference on learning representations"},{"key":"8182_CR18","first-page":"1","volume":"36","author":"T Dettmers","year":"2024","unstructured":"Dettmers T et al (2024) Qlora: efficient finetuning of quantized LLMS. Adv Neural Inf Process Syst 36:1","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"8182_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu Y et al (2021) Domain-specific language model pretraining for biomedical natural language processing. ACM Trans Comput Healthc 3(1):1\u201323","journal-title":"ACM Trans Comput Healthc"},{"key":"8182_CR20","unstructured":"Mikolov T (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781"},{"key":"8182_CR21","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp\u00a01532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"issue":"1","key":"8182_CR22","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41746-023-00896-7","volume":"6","author":"L Tang","year":"2023","unstructured":"Tang L et al (2023) Evaluating large language models on medical evidence summarization. NPJ Dig Med 6(1):158","journal-title":"NPJ Dig Med"},{"key":"8182_CR23","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230364","volume":"1","author":"B Le Guellec","year":"2024","unstructured":"Le Guellec B et al (2024) Performance of an open-source large language model in extracting information from free-text radiology reports. Radiol Artif Intell 1:e230364","journal-title":"Radiol Artif Intell"},{"issue":"9","key":"8182_CR24","doi-asserted-by":"publisher","first-page":"btad557","DOI":"10.1093\/bioinformatics\/btad557","volume":"39","author":"Q Chen","year":"2023","unstructured":"Chen Q et al (2023) An extensive benchmark study on biomedical text generation and mining with ChatGPT. Bioinformatics 39(9):btad557","journal-title":"Bioinformatics"},{"key":"8182_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2024.3373439","volume":"1","author":"J Li","year":"2024","unstructured":"Li J et al (2024) Benchmarking large language models in evidence-based medicine. IEEE J Biomed Health Inform 1:1","journal-title":"IEEE J Biomed Health Inform"},{"key":"8182_CR26","doi-asserted-by":"publisher","DOI":"10.2196\/55318","volume":"12","author":"S Sivarajkumar","year":"2024","unstructured":"Sivarajkumar S et al (2024) An empirical evaluation of prompting strategies for large language models in zero-shot clinical natural language processing: algorithm development and validation study. JMIR Med Inform 12:e55318","journal-title":"JMIR Med Inform"},{"issue":"5","key":"8182_CR27","doi-asserted-by":"publisher","first-page":"AIoa2300151","DOI":"10.1056\/AIoa2300151","volume":"1","author":"NR Rydzewski","year":"2024","unstructured":"Rydzewski NR et al (2024) Comparative evaluation of LLMs in clinical oncology. NEJM AI 1(5):AIoa2300151","journal-title":"NEJM AI"},{"issue":"6","key":"8182_CR28","doi-asserted-by":"publisher","first-page":"bbac409","DOI":"10.1093\/bib\/bbac409","volume":"23","author":"R Luo","year":"2022","unstructured":"Luo R et al (2022) BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings Bioinform 23(6):bbac409. https:\/\/doi.org\/10.1093\/bib\/bbac409","journal-title":"Briefings Bioinform"},{"issue":"7972","key":"8182_CR29","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal K et al (2023) Large language models encode clinical knowledge. Nature 620(7972):172\u2013180. https:\/\/doi.org\/10.1038\/s41586-023-06291-2","journal-title":"Nature"},{"key":"8182_CR30","unstructured":"Toma A et al (2023) Clinical camel: an open-source expert-level medical language model with dialogue-based knowledge encoding. arXiv preprint arXiv: 2305.12031 [cs.CL]"},{"issue":"1","key":"8182_CR31","doi-asserted-by":"publisher","first-page":"3280","DOI":"10.1038\/s41467-025-56989-2","volume":"16","author":"Q Chen","year":"2025","unstructured":"Chen Q et al (2025) Benchmarking large language models for biomedical natural language processing applications and recommendations. Nat Commun 16(1):3280. https:\/\/doi.org\/10.1038\/s41467-025-56989-2","journal-title":"Nat Commun"},{"key":"8182_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.103003","volume":"157","author":"A Bonfigli","year":"2024","unstructured":"Bonfigli A et al (2024) From pre-training to fine-tuning: an in-depth analysis of large language models in the biomedical domain. Artif Intell Med 157:103003. https:\/\/doi.org\/10.1016\/j.artmed.2024.103003","journal-title":"Artif Intell Med"},{"issue":"9","key":"8182_CR33","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1093\/jamia\/ocae122","volume":"31","author":"H Tran","year":"2024","unstructured":"Tran H et al (2024) BioInstruct: instruction tuning of large language models for biomedical natural language processing. J Am Med Inform Assoc 31(9):1821\u20131832. https:\/\/doi.org\/10.1093\/jamia\/ocae122","journal-title":"J Am Med Inform Assoc"},{"issue":"6","key":"8182_CR34","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1093\/jamia\/ocaf045","volume":"32","author":"FJ Dorfner","year":"2025","unstructured":"Dorfner FJ et al (2025) Evaluating the effectiveness of biomedical fine-tuning for large language models on clinical tasks. J Am Med Inform Assoc 32(6):1015\u20131024. https:\/\/doi.org\/10.1093\/jamia\/ocaf045","journal-title":"J Am Med Inform Assoc"},{"key":"8182_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1101\/2024.05.17.24307411","volume":"1","author":"H Feng","year":"2024","unstructured":"Feng H et al (2024) Evaluation of large language model performance on the biomedical language understanding and reasoning benchmark. Comparative study. medRxiv 1:1. https:\/\/doi.org\/10.1101\/2024.05.17.24307411","journal-title":"medRxiv"},{"issue":"1","key":"8182_CR36","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s12859-022-04688-w","volume":"23","author":"U Naseem","year":"2022","unstructured":"Naseem U et al (2022) Benchmarking for biomedical natural language processing tasks with a domain specific ALBERT. BMC Bioinform 23(1):144. https:\/\/doi.org\/10.1186\/s12859-022-04688-w","journal-title":"BMC Bioinform"},{"key":"8182_CR37","doi-asserted-by":"crossref","unstructured":"Li J et al (2024) Towards instruction-tuned verification for improving biomedical information extraction with large language models. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE 2024, pp\u00a06685\u20136692","DOI":"10.1109\/BIBM62325.2024.10822624"},{"key":"8182_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107388","volume":"103","author":"Z Yin","year":"2025","unstructured":"Yin Z et al (2025) A novel approach to unlocking the synergy of large language models and chemical knowledge in biomedical signal applications. Biomed Signal Process Control 103:107388","journal-title":"Biomed Signal Process Control"},{"key":"8182_CR39","unstructured":"Tay Y et al (2022) Ul2: unifying language learning paradigms. arXiv preprint arXiv:2205.05131"},{"issue":"70","key":"8182_CR40","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung HW et al (2024) Scaling instruction-finetuned language models. J Mach Learn Res 25(70):1\u201353","journal-title":"J Mach Learn Res"},{"key":"8182_CR41","unstructured":"Touvron H et al (2023) Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"8182_CR42","unstructured":"Team GLM et al (2024) Chatglm: a family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793"},{"key":"8182_CR43","doi-asserted-by":"crossref","unstructured":"Smilga J, Alabiad Y (2024) T\u00fcDuo at SemEval 2024 Task 2: flan-T5 and data augmentation for biomedical natural language inference. In: Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval 2024). Association for Computational Linguistics","DOI":"10.18653\/v1\/2024.semeval-1.106"},{"key":"8182_CR44","unstructured":"Sim Y, Sammut-Powell C, Kurz D (2023) Generating lay summaries of biomedical articles using large language models. In: Proceedings of the 22nd Workshop on Biomedical Natural Language Processing. BioLaySumm Shared Task, FLAN-T5 USED as a Baseline"},{"key":"8182_CR45","doi-asserted-by":"crossref","unstructured":"Song X et al (2025) Stroke diagnosis and prediction tool using ChatGLM: development and validation study. In: JMIR Medical Informatics (2025). ChatGLM-Based Clinical Decision Support for Stroke","DOI":"10.2196\/preprints.67010"},{"key":"8182_CR46","first-page":"1","volume":"1","author":"C Liu","year":"2024","unstructured":"Liu C et al (2024) CPMI-ChatGLM: parameter-efficient fine-tuning of ChatGLM with Chinese patent medicine instructions. Sci Rep 1:1","journal-title":"Sci Rep"},{"key":"8182_CR47","unstructured":"Chen Y et al (2024) Evaluating a ChatGLM-based model for real-world clinical data extraction. In: European Heart Journal\u2014Digital Health. Applies ChatGLM to Extraction from Cardiology Records"},{"key":"8182_CR48","doi-asserted-by":"publisher","unstructured":"Nye B et al (2018) A corpus with multi-level annotations of patients, interventions and outcomes to support language processing for medical literature. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Melbourne, Australia: Association for Computational Linguistics, pp\u00a0197\u2013207. https:\/\/doi.org\/10.18653\/v1\/P18-1019","DOI":"10.18653\/v1\/P18-1019"},{"key":"8182_CR49","doi-asserted-by":"crossref","unstructured":"Lester B, Al-Rfou R, Constant N (2021) The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp\u00a03045\u20133059","DOI":"10.18653\/v1\/2021.emnlp-main.243"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-08182-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-08182-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-08182-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:14:21Z","timestamp":1769505261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-08182-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,27]]},"references-count":49,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["8182"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-08182-x","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,27]]},"assertion":[{"value":"14 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 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 that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study does not involve any human participants, animal experiments, or clinical trials. All data used in the research were collected from publicly available sources. As no new data involving human participants or animals were collected, ethical approval was not required for this research. The authors affirm that the study complies with all ethical guidelines and regulations pertaining to data use and research conduct. The privacy rights of individuals were strictly observed throughout the research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"103"}}