{"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/fine-tuning-large-language-models-with-human","title":"Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering","arxiv_id":"2408.07888","date":"2024-08-15","proceeding":null,"authors":["Yushi Yang","Andrew M. Bean","Robert McCraith","Adam Mahdi"],"abstract":"Fine-tuning Large Language Models (LLMs) incurs considerable training costs, driving the need for data-efficient training with optimised data ordering. Human-inspired strategies offer a solution by organising data based on human learning practices. This study evaluates the fine-tuning efficiency of five human-inspired strategies across four language models, three datasets, and both human- and LLM-labelled data in the context of medical question answering. These strategies achieve the best accuracy gain of 1.81% and an average gain of 1.02% across datasets, with interleaved strategies delivering the best average results. However, the best strategy varies across model-dataset combinations, limiting the generalisability of the effects of any single strategy. Additionally, LLM-defined question difficulty outperforms human-defined labels in curriculum-based learning, showing the potential of model-generated data as a cost-effective alternative for optimising fine-tuning.","url_abs":"https://arxiv.org/abs/2408.07888v2","url_pdf":"https://arxiv.org/pdf/2408.07888v2.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":"fine-tuning-large-language-models-with-human","repo_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"fine-tuning-large-language-models-with-human","repo_url":"https://github.com/yushi-y/dpo-toxic-neurons","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"Medical Question Answering"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.07888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07888"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/Oxford-AI-for-Society/human-learning-strategies","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yushi-y/dpo-toxic-neurons","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":10,"samples":[{"code_sha256_prefix":"96356927ed487a5e","entry":"arrange_emh","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/data_ordering.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/data_ordering.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"96356927ed487a5e"}},{"code_sha256_prefix":"57123d949a952552","entry":"calculate_metrics","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/inference/inference.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"57123d949a952552"}},{"code_sha256_prefix":"6b8d0b080c88a595","entry":"evaluate_model_on_dataset","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/inference/inference.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6b8d0b080c88a595"}},{"code_sha256_prefix":"6ea1d20b1706f31c","entry":"format_example","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/fine_tuning/shared_utils.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/fine_tuning/shared_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6ea1d20b1706f31c"}},{"code_sha256_prefix":"a4fee013a494fc35","entry":"score_clusters","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"text_clustering.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/text_clustering.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a4fee013a494fc35"}},{"code_sha256_prefix":"40db29f20ec31a60","entry":"evaluate_model_on_dataset_four_options","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/inference/inference.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/inference/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"40db29f20ec31a60"}},{"code_sha256_prefix":"7d5a58e9f94a2380","entry":"interleaved","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/data_ordering.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/data_ordering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7d5a58e9f94a2380"}},{"code_sha256_prefix":"aeb5b885c40bfaad","entry":"interleaved_emh","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/data_ordering.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/data_ordering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"aeb5b885c40bfaad"}},{"code_sha256_prefix":"912f3b9102f82700","entry":"load_model","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/fine_tuning/shared_utils.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/fine_tuning/shared_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"912f3b9102f82700"}},{"code_sha256_prefix":"12071bb621f4cba1","entry":"load_tokenizer","repo":"Oxford-AI-for-Society/human-learning-strategies","repo_kind":"official","path":"training/fine_tuning/shared_utils.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/fine_tuning/shared_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"12071bb621f4cba1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}