{"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/medconceptsqa-open-source-medical-concepts-qa","title":"MedConceptsQA: Open Source Medical Concepts QA Benchmark","arxiv_id":"2405.07348","date":"2024-05-12","proceeding":null,"authors":["Ofir Ben Shoham","Nadav Rappoport"],"abstract":"We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across different vocabularies: diagnoses, procedures, and drugs. The questions are categorized into three levels of difficulty: easy, medium, and hard. We conducted evaluations of the benchmark using various Large Language Models. Our findings show that pre-trained clinical Large Language Models achieved accuracy levels close to random guessing on this benchmark, despite being pre-trained on medical data. However, GPT-4 achieves an absolute average improvement of nearly 27%-37% (27% for zero-shot learning and 37% for few-shot learning) when compared to clinical Large Language Models. Our benchmark serves as a valuable resource for evaluating the understanding and reasoning of medical concepts by Large Language Models. Our benchmark is available at https://huggingface.co/datasets/ofir408/MedConceptsQA","url_abs":"https://arxiv.org/abs/2405.07348v2","url_pdf":"https://arxiv.org/pdf/2405.07348v2.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":"medconceptsqa-open-source-medical-concepts-qa","repo_url":"https://github.com/nadavlab/MedConceptsQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"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":[{"slug":"medconceptsqa","name":"MedConceptsQA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-learning-on-medconceptsqa","task":"Few-Shot Learning","dataset":"MedConceptsQA","model":"johnsnowlabs/JSL-MedMNX-7B","rank_in_archive_order":4,"of":12,"metrics":{"Accuracy":"25.627"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.07348","atlas_url":"https://app.syntology.ai/?focus=2405.07348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07348"}},"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/nadavlab/MedConceptsQA","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"667892ff3e170d62","entry":"is_leaf","repo":"nadavlab/MedConceptsQA","repo_kind":"official","path":"create_benchmark.py","file_url":"https://github.com/nadavlab/MedConceptsQA/blob/HEAD/create_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"667892ff3e170d62"}},{"code_sha256_prefix":"3db84ba5872a0e8f","entry":"parse_gpt_response","repo":"nadavlab/MedConceptsQA","repo_kind":"official","path":"gpt4_runner.py","file_url":"https://github.com/nadavlab/MedConceptsQA/blob/HEAD/gpt4_runner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3db84ba5872a0e8f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}