{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/alpacare-instruction-tuned-large-language","title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","arxiv_id":"2310.14558","date":"2023-10-23","proceeding":null,"authors":["Xinlu Zhang","Chenxin Tian","Xianjun Yang","Lichang Chen","Zekun Li","Linda Ruth Petzold"],"abstract":"Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications. However, previous studies mainly fine-tune LLMs on biomedical datasets with limited diversity, which often rely on benchmarks or narrow task scopes, and hence significantly limit the effectiveness on their medical instruction-following ability and generalizability. To bridge this gap, we propose creating a diverse, machine-generated medical IFT dataset, MedInstruct-52k, using GPT-4 and ChatGPT with a high-quality expert-curated seed set. We then fine-tune LLaMA-series models on the dataset to develop AlpaCare. Despite using a smaller domain-specific dataset than previous medical LLMs, AlpaCare not only demonstrates superior performance on medical applications, with up to 38.1% absolute gain over best baselines in medical free-form instruction evaluations, but also achieves 6.7% absolute gains averaged over multiple general domain benchmarks. Human evaluation further shows that AlpaCare consistently outperforms best baselines in terms of both correctness and helpfulness. We offer public access to our data, model, and codebase in https://github.com/XZhang97666/AlpaCare.","url_abs":"https://arxiv.org/abs/2310.14558v6","url_pdf":"https://arxiv.org/pdf/2310.14558v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"alpacare-instruction-tuned-large-language","repo_url":"https://github.com/xzhang97666/alpacare","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.14558","atlas_url":"https://app.syntology.ai/?focus=2310.14558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14558"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xzhang97666/alpacare","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1f5f12c2a05ea647","entry":"anthropic_output_generation_encode_prompt","repo":"xzhang97666/alpacare","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f5f12c2a05ea647"}},{"code_sha256_prefix":"78817ba27701dad2","entry":"dict_win_calculate","repo":"xzhang97666/alpacare","repo_kind":"official","path":"evaluation/evaulation.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/evaluation/evaulation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"78817ba27701dad2"}},{"code_sha256_prefix":"190ccfddff487a04","entry":"gpt_output_generation_encode_prompt","repo":"xzhang97666/alpacare","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"190ccfddff487a04"}},{"code_sha256_prefix":"68049481975af918","entry":"load_or_convert_to_dataframe","repo":"xzhang97666/alpacare","repo_kind":"official","path":"utils.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68049481975af918"}},{"code_sha256_prefix":"817d5f759487007d","entry":"preprocess","repo":"xzhang97666/alpacare","repo_kind":"official","path":"training/train_alpaca.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/training/train_alpaca.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"817d5f759487007d"}},{"code_sha256_prefix":"4ea89f17e5ce4df2","entry":"remove_special_characters","repo":"xzhang97666/alpacare","repo_kind":"official","path":"evaluation/evaulation.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/evaluation/evaulation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4ea89f17e5ce4df2"}},{"code_sha256_prefix":"72f54c10c0e56d6a","entry":"str_win_calculate","repo":"xzhang97666/alpacare","repo_kind":"official","path":"evaluation/evaulation.py","file_url":"https://github.com/xzhang97666/alpacare/blob/HEAD/evaluation/evaulation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72f54c10c0e56d6a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}