{"doi":"10.1093/jamia/ocae122","title":"BioInstruct: instruction tuning of large language models for biomedical natural language processing","abstract":"OBJECTIVES: To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles. MATERIALS AND METHODS: We created the BioInstruct, comprising 25 005 instructions to instruction-tune LLMs (LLaMA 1 and 2, 7B and 13B version). The instructions were created by prompting the GPT-4 language model with 3-seed samples randomly drawn from an 80 human curated instructions. We employed Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We then evaluated these instruction-tuned LLMs on several BioNLP tasks, which can be grouped into 3 major categories: question answering (QA), information extraction (IE), and text generation (GEN). We also examined whether categories (eg, QA, IE, and generation) of instructions impact model performance. RESULTS AND DISCUSSION: Comparing with LLMs without instruction-tuned, our instruction-tuned LLMs demonstrated marked performance gains: 17.3% in QA on average accuracy metric, 5.7% in IE on average F1 metric, and 96% in Generation tasks on average GPT-4 score metric. Our 7B-parameter instruction-tuned LLaMA 1 model was competitive or even surpassed other LLMs in the biomedical domain that were also fine-tuned from LLaMA 1 with vast domain-specific data or a variety of tasks. Our results also show that the performance gain is significantly higher when instruction fine-tuning is conducted with closely related tasks. Our findings align with the observations of multi-task learning, suggesting the synergies between 2 tasks. CONCLUSION: The BioInstruct dataset serves as a valuable resource and instruction tuned LLMs lead to the best performing BioNLP applications.","journal":"Journal of the American Medical Informatics Association","year":2024,"id":418478,"datarank":1.6391067070564436,"base_score":3.9318256327243257,"endowment":3.9318256327243257,"self_citation_contribution":0.5897738449086489,"citation_network_contribution":1.0493328621477946,"self_endowment_contribution":0.5897738449086489,"citer_contribution":1.0493328621477946,"corpus_percentile":87.2979036125938,"corpus_rank":1643,"citation_count":50,"citer_count":47,"citers_with_citation_signal":28,"citers_with_endowment":28,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.9081,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":81059,"name":"ZhiChao Yang","orcid":"0000-0002-2797-4257","position":1,"is_corresponding":false},{"id":984573,"name":"Zonghai Yao","orcid":"0000-0002-5707-8410","position":2,"is_corresponding":false},{"id":1206114,"name":"Hong Yu","orcid":"0000-0003-2248-5056","position":3,"is_corresponding":false},{"id":1206113,"name":"Hieu Tran","orcid":"0000-0002-0067-0683","position":0,"is_corresponding":true}],"reference_count":13,"raw_metadata":null,"created_at":"2026-07-19T01:57:02.483590Z","pmid":"38833265","pmcid":"PMC11339494","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}