{"url":"/dataset/frenchmedmcqa","name":"FrenchMedMCQA","full_name":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","description_markdown":"This paper introduces FrenchMedMCQA, the first publicly available Multiple-Choice Question Answering (MCQA) dataset in French for medical domain. It is composed of 3,105 questions taken from real exams of the French medical specialization diploma in pharmacy, mixing single and multiple answers. Each instance of the dataset contains an identifier, a question, five possible answers and their manual correction(s). We also propose first baseline models to automatically process this MCQA task in order to report on the current performances and to highlight the difficulty of the task. A detailed analysis of the results showed that it is necessary to have representations adapted to the medical domain or to the MCQA task: in our case, English specialized models yielded better results than generic French ones, even though FrenchMedMCQA is in French. Corpus, models and tools are available online.","description_withheld":null,"homepage":"https://github.com/qanastek/FrenchMedMCQA","introduced_date":"2022-10-22","introduced_date_note":null,"introduced_by":null,"license":{"name":"Apache 2.0","url":"https://www.apache.org/licenses/LICENSE-2.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Biomedical","url":"/datasets/modality/biomedical"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Multiple Choice Question Answering (MCQA)","url":"/task/multiple-choice-qa","datasets_with_task":"/datasets/task/multiple-choice-qa"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"},{"name":"Generative Question Answering","url":"/task/generative-question-answering","datasets_with_task":"/datasets/task/generative-question-answering"},{"name":"Science Question Answering","url":"/task/science-question-answering","datasets_with_task":"/datasets/task/science-question-answering"},{"name":"Question-Answer-Generation","url":"/task/question-answer-generation","datasets_with_task":"/datasets/task/question-answer-generation"}],"languages":[{"name":"French","url":"/datasets/language/french"}],"variants":["FrenchMedMCQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qanastek/LLaMaInstructionsFrenchMedMCQA","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qanastek/frenchmedmcqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/DEFT-2023/DEFT2023","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qanastek/FrenchMedMCQA","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-22","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"FrenchMedMCQA","rows":2,"metrics":["Exact Match Accuracy","Hamming Score"],"first_row_in_archive_order":{"model":"CamemBERT","paper":"/paper/frenchmedmcqa-a-french-multiple-choice-1","metrics":{"Exact Match Accuracy":"16.55","Hamming Score":"36.24"},"code_links":[{"title":"qanastek/FrenchMedMCQA","url":"https://github.com/qanastek/FrenchMedMCQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/frenchmedmcqa-a-french-multiple-choice-1","title":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","date":"2023-04-09","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}