{"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/pmc-vqa-visual-instruction-tuning-for-medical","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","arxiv_id":"2305.10415","date":"2023-05-17","proceeding":null,"authors":["Xiaoman Zhang","Chaoyi Wu","Ziheng Zhao","Weixiong Lin","Ya zhang","Yanfeng Wang","Weidi Xie"],"abstract":"Medical Visual Question Answering (MedVQA) presents a significant opportunity to enhance diagnostic accuracy and healthcare delivery by leveraging artificial intelligence to interpret and answer questions based on medical images. In this study, we reframe the problem of MedVQA as a generation task that naturally follows the human-machine interaction and propose a generative-based model for medical visual understanding by aligning visual information from a pre-trained vision encoder with a large language model. We establish a scalable pipeline to construct a large-scale medical visual question-answering dataset, named PMC-VQA, which contains 227k VQA pairs of 149k images that cover various modalities or diseases. We train the proposed model on PMC-VQA and then fine-tune it on multiple public benchmarks, e.g., VQA-RAD, SLAKE, and Image-Clef-2019, significantly outperforming existing MedVQA models in generating relevant, accurate free-form answers. In addition, we propose a test set that has undergone manual verification, which is significantly more challenging, serving to better monitor the development of generative MedVQA methods. To facilitate comprehensive evaluation and comparison, we have maintained a leaderboard at https://paperswithcode.com/paper/pmc-vqa-visual-instruction-tuning-for-medical, offering a centralized resource for tracking progress and benchmarking state-of-the-art approaches. The PMC-VQA dataset emerges as a vital resource for the field of research, and the MedVInT presents a significant breakthrough in the area of MedVQA.","url_abs":"https://arxiv.org/abs/2305.10415v6","url_pdf":"https://arxiv.org/pdf/2305.10415v6.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":"pmc-vqa-visual-instruction-tuning-for-medical","repo_url":"https://github.com/xiaoman-zhang/PMC-VQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pmc-vqa-visual-instruction-tuning-for-medical","repo_url":"https://github.com/zihanzhaosjtu/librisqa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"generative-visual-question-answering","task_name":"Generative Visual Question Answering"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"medical-visual-question-answering","task_name":"Medical Visual Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"pmc-vqa","name":"PMC-VQA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/generative-visual-question-answering-on-pmc","task":"Generative Visual Question Answering","dataset":"PMC-VQA","model":"MedVInT","rank_in_archive_order":1,"of":3,"metrics":{"BLEU-1":"23.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-pmc-vqa","task":"Visual Question Answering (VQA)","dataset":"PMC-VQA","model":"MedVInT","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"42.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10415"}},"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/zihanzhaosjtu/librisqa","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaoman-zhang/PMC-VQA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"78ca1debd9c4ed87","entry":"autocontrast_func","repo":"xiaoman-zhang/PMC-VQA","repo_kind":"official","path":"src/MedVInT_TD/Dataset/randaugment.py","file_url":"https://github.com/xiaoman-zhang/PMC-VQA/blob/HEAD/src/MedVInT_TD/Dataset/randaugment.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78ca1debd9c4ed87"}},{"code_sha256_prefix":"4c53169f63a1fcef","entry":"equalize_func","repo":"xiaoman-zhang/PMC-VQA","repo_kind":"official","path":"src/MedVInT_TD/Dataset/randaugment.py","file_url":"https://github.com/xiaoman-zhang/PMC-VQA/blob/HEAD/src/MedVInT_TD/Dataset/randaugment.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c53169f63a1fcef"}},{"code_sha256_prefix":"1dd2ab205689d45b","entry":"identity_func","repo":"xiaoman-zhang/PMC-VQA","repo_kind":"official","path":"src/MedVInT_TD/Dataset/randaugment.py","file_url":"https://github.com/xiaoman-zhang/PMC-VQA/blob/HEAD/src/MedVInT_TD/Dataset/randaugment.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1dd2ab205689d45b"}},{"code_sha256_prefix":"9b5765523c6d17fd","entry":"freeze_batch_norm_2d","repo":"xiaoman-zhang/PMC-VQA","repo_kind":"official","path":"src/MedVInT_TE/models/pmc_oa/utils.py","file_url":"https://github.com/xiaoman-zhang/PMC-VQA/blob/HEAD/src/MedVInT_TE/models/pmc_oa/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b5765523c6d17fd"}},{"code_sha256_prefix":"f6b75db5ff056cee","entry":"get_peft_config","repo":"xiaoman-zhang/PMC-VQA","repo_kind":"official","path":"src/MedVInT_TE/models/llama/vqa_model.py","file_url":"https://github.com/xiaoman-zhang/PMC-VQA/blob/HEAD/src/MedVInT_TE/models/llama/vqa_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b75db5ff056cee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}