{"id":"https://openalex.org/W4404782337","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.1119","title":"Self-Training Large Language and Vision Assistant for Medical Question Answering","display_name":"Self-Training Large Language and Vision Assistant for Medical Question Answering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782337","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.1119"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.1119","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.1119","pdf_url":"https://aclanthology.org/2024.emnlp-main.1119.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.1119.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020054896","display_name":"Guohao Sun","orcid":"https://orcid.org/0009-0002-0935-6196"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guohao Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021042598","display_name":"Can Qin","orcid":"https://orcid.org/0000-0003-0712-5378"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Can Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010970485","display_name":"Huazhu Fu","orcid":"https://orcid.org/0000-0002-9702-5524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huazhu Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045732749","display_name":"Linwei Wang","orcid":"https://orcid.org/0000-0001-5406-1034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linwei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021486404","display_name":"Zhiqiang Tao","orcid":"https://orcid.org/0000-0002-5639-7540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqiang Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2004,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93808393,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"20052","last_page":"20060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6869000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6869000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.6371999979019165,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.8234831690788269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6980977654457092},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5554707646369934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5349956750869751},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5251837968826294}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8234831690788269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980977654457092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5554707646369934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5349956750869751},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5251837968826294},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.1119","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.1119","pdf_url":"https://aclanthology.org/2024.emnlp-main.1119.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.1119","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.1119","pdf_url":"https://aclanthology.org/2024.emnlp-main.1119.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782337.pdf","grobid_xml":"https://content.openalex.org/works/W4404782337.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0,52],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"shown":[5],"significant":[6],"potential":[7],"in":[8,41],"assisting":[9],"medical":[10,20,43,74,133,151],"diagnosis":[11],"by":[12],"leveraging":[13],"extensive":[14],"biomedical":[15,100],"datasets.However,":[16],"the":[17,42,104,109,113,123,144,150],"advancement":[18],"of":[19,72,128,146,149],"image":[21],"understanding":[22],"and":[23,36,54,91,125],"reasoning":[24],"critically":[25],"depends":[26],"on":[27,108],"building":[28],"high-quality":[29],"visual":[30,75],"instruction":[31,76],"data,":[32,111],"which":[33],"is":[34,62,96,154],"costly":[35],"labor-intensive":[37],"to":[38,64,78,102,116],"obtain,":[39],"particularly":[40],"domain.To":[44],"mitigate":[45],"this":[46],"data-starving":[47],"issue,":[48],"we":[49],"introduce":[50],"Self-Training":[51],"Language":[53],"Vision":[55],"Assistant":[56],"for":[57],"Medicine":[58],"(STLLaVA-Med).The":[59],"proposed":[60],"method":[61],"designed":[63],"train":[65],"a":[66,88,99],"policy":[67,114],"model":[68,115],"(an":[69],"LVLM)":[70],"capable":[71],"auto-generating":[73],"data":[77,80,126],"improve":[79],"efficiency,":[81],"guided":[82],"through":[83],"Direct":[84],"Preference":[85],"Optimization":[86],"(DPO).Specifically,":[87],"more":[89],"powerful":[90],"larger":[92],"LVLM":[93],"(e.g.,":[94],"GPT-4o)":[95],"involved":[97],"as":[98],"expert":[101],"oversee":[103],"DPO":[105],"fine-tuning":[106],"process":[107],"auto-generated":[110],"encouraging":[112],"align":[117],"efficiently":[118],"with":[119,143],"human":[120],"preferences.We":[121],"validate":[122],"efficacy":[124],"efficiency":[127],"STLLaVA-Med":[129],"across":[130],"three":[131],"major":[132],"Visual":[134],"Question":[135],"Answering":[136],"(VQA)":[137],"benchmarks,":[138],"demonstrating":[139],"competitive":[140],"zero-shot":[141],"performance":[142],"utilization":[145],"only":[147],"9%":[148],"data.Our":[152],"implementation":[153],"available":[155],"at":[156],"https:":[157],"//github.com/heliossun/STLLaVA-Med.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}