{"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/stllava-med-self-training-large-language-and","title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering","arxiv_id":"2406.19973","date":"2024-06-28","proceeding":null,"authors":["Guohao Sun","Can Qin","Huazhu Fu","Linwei Wang","Zhiqiang Tao"],"abstract":"Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce Self-Training Large Language and Vision Assistant for Medicine (STLLaVA-Med). The proposed method is designed to train a policy model (an LVLM) capable of auto-generating medical visual instruction data to improve data efficiency, guided through Direct Preference Optimization (DPO). Specifically, a more powerful and larger LVLM (e.g., GPT-4o) is involved as a biomedical expert to oversee the DPO fine-tuning process on the auto-generated data, encouraging the policy model to align efficiently with human preferences. We validate the efficacy and data efficiency of STLLaVA-Med across three major medical Visual Question Answering (VQA) benchmarks, demonstrating competitive zero-shot performance with the utilization of only 9% of the medical data.","url_abs":"https://arxiv.org/abs/2406.19973v2","url_pdf":"https://arxiv.org/pdf/2406.19973v2.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":"stllava-med-self-training-large-language-and","repo_url":"https://github.com/heliossun/stllava-med","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"medical-diagnosis","task_name":"Medical Diagnosis"},{"task_slug":null,"task_name":"Medical Question Answering"},{"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":"align","method_name":"ALIGN"},{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.19973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19973"}},"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/heliossun/stllava-med","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/heliossun/STLLaVA-Med","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":3,"ran_fixture":1,"unverified":10},"by_repo_kind":{"official":{"samples":19,"ran":9,"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":"ee3792b1ae45cbb6","entry":"CLIPVisionTower","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee3792b1ae45cbb6"}},{"code_sha256_prefix":"b2d62e11a466c119","entry":"Clustering","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2d62e11a466c119"}},{"code_sha256_prefix":"9f0f5d62445adabe","entry":"IdentityMap","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f0f5d62445adabe"}},{"code_sha256_prefix":"e9cfb7ae423d3e3a","entry":"LlavaConfig","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9cfb7ae423d3e3a"}},{"code_sha256_prefix":"990ae00bb84c8cce","entry":"QuickGELU","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"990ae00bb84c8cce"}},{"code_sha256_prefix":"fba2ee2fd7519dce","entry":"build_vision_projector","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fba2ee2fd7519dce"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"heliossun/stllava-med","repo_kind":"official","path":"llava/eval/model_cap.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/llava/eval/model_cap.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"heliossun/stllava-med","repo_kind":"official","path":"llava/eval/model_cap.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/llava/eval/model_cap.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"10893c4608c08075","entry":"split_to_even_chunks","repo":"heliossun/stllava-med","repo_kind":"official","path":"llava_dpo_trainer.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/llava_dpo_trainer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10893c4608c08075"}},{"code_sha256_prefix":"846e78137649eefe","entry":"LlavaLlamaForCausalLM","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.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":"846e78137649eefe"}},{"code_sha256_prefix":"7687df6fa2a321f7","entry":"LlavaLlamaModel","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.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":"7687df6fa2a321f7"}},{"code_sha256_prefix":"9392f432fde94da9","entry":"LlavaMetaForCausalLM","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.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":"9392f432fde94da9"}},{"code_sha256_prefix":"616ce829130b1d59","entry":"LlavaMetaModel","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.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":"616ce829130b1d59"}},{"code_sha256_prefix":"b95671438fbf50fa","entry":"build_vision_tower","repo":"heliossun/STLLaVA-Med","repo_kind":"official","path":"llava/model/language_model/llava_llama.py","file_url":"https://github.com/heliossun/STLLaVA-Med/blob/HEAD/llava/model/language_model/llava_llama.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":"b95671438fbf50fa"}},{"code_sha256_prefix":"bb35e3ac741bb2c9","entry":"get_mm_adapter_state_maybe_zero_3","repo":"heliossun/stllava-med","repo_kind":"official","path":"llava_dpo_trainer.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/llava_dpo_trainer.py","link_basis":"harvester_set","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":"bb35e3ac741bb2c9"}},{"code_sha256_prefix":"fa1225dfac92bc0d","entry":"get_peft_state_maybe_zero_3","repo":"heliossun/stllava-med","repo_kind":"official","path":"train_dpo.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/train_dpo.py","link_basis":"harvester_set","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":"fa1225dfac92bc0d"}},{"code_sha256_prefix":"1c53657305b66e9f","entry":"get_peft_state_non_lora_maybe_zero_3","repo":"heliossun/stllava-med","repo_kind":"official","path":"train_dpo.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/train_dpo.py","link_basis":"harvester_set","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":"1c53657305b66e9f"}},{"code_sha256_prefix":"735025744c1ab0cf","entry":"maybe_zero_3","repo":"heliossun/stllava-med","repo_kind":"official","path":"llava_dpo_trainer.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/llava_dpo_trainer.py","link_basis":"harvester_set","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":"735025744c1ab0cf"}},{"code_sha256_prefix":"616ffbdc154ed2d8","entry":"maybe_zero_3","repo":"heliossun/stllava-med","repo_kind":"official","path":"train_dpo.py","file_url":"https://github.com/heliossun/stllava-med/blob/HEAD/train_dpo.py","link_basis":"harvester_set","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":"616ffbdc154ed2d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}