{"id":"https://openalex.org/W7164865706","doi":"https://doi.org/10.1145/3805622.3810670","title":"EC-RAG: Evidence-Centric Retrieval-Augmented Generation for Medical Visual Question Answering","display_name":"EC-RAG: Evidence-Centric Retrieval-Augmented Generation for Medical Visual Question Answering","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164865706","doi":"https://doi.org/10.1145/3805622.3810670"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810670","pdf_url":null,"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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810670","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122614848","display_name":"Li S","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songming Li","raw_affiliation_strings":["Central South University, Changsha, hunan, China"],"raw_orcid":"https://orcid.org/0009-0003-1705-0573","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138674621","display_name":"Jun Long","orcid":"https://orcid.org/0009-0003-2780-1115"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Long","raw_affiliation_strings":["Central South University, Changsha, hunan, China"],"raw_orcid":"https://orcid.org/0009-0003-2780-1115","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, hunan, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7486139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2760","last_page":"2767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002099999925121665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7075999975204468},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5336999893188477},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4661000072956085},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4133000075817108},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3978999853134155},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.3882000148296356},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.34529998898506165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387999892234802},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7075999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6323999762535095},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4659999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43700000643730164},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42829999327659607},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.34529998898506165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C544519230","wikidata":"https://www.wikidata.org/wiki/Q32566","display_name":"Computed tomography","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2515999972820282},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810670","pdf_url":null,"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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810670","pdf_url":null,"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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2152772232","https://openalex.org/W2995225687","https://openalex.org/W4384561707","https://openalex.org/W4388409299","https://openalex.org/W4400128031","https://openalex.org/W4402582321","https://openalex.org/W4402670290","https://openalex.org/W4402671555","https://openalex.org/W4402753927","https://openalex.org/W4402774103","https://openalex.org/W4404622689","https://openalex.org/W4404783798","https://openalex.org/W4406152279","https://openalex.org/W4406887664","https://openalex.org/W4410536678","https://openalex.org/W4411120278","https://openalex.org/W4413447271","https://openalex.org/W7133193597","https://openalex.org/W7133197087","https://openalex.org/W7133220561","https://openalex.org/W7133253450"],"related_works":[],"abstract_inverted_index":{"Medical":[0],"Visual":[1],"Question":[2],"Answering":[3],"(Med-VQA)":[4],"necessitates":[5],"rigorous":[6],"knowledge-grounded":[7],"reasoning":[8],"to":[9,50,68],"emulate":[10],"the":[11,32,66,97,121],"active":[12,70],"hypothetico-deductive":[13],"diagnosis":[14],"of":[15,138],"clinical":[16],"experts.":[17],"However,":[18],"current":[19],"Retrieval-Augmented":[20],"Generation":[21],"(RAG)":[22],"approaches":[23],"remain":[24],"bound":[25],"by":[26,73],"a":[27,115],"passive":[28],"retrieval":[29],"paradigm,":[30],"where":[31],"reliance":[33],"on":[34,96,120],"raw":[35],"queries":[36],"and":[37,44,89,101,125,142],"coarse":[38],"similarity":[39],"scores":[40],"creates":[41],"significant":[42],"semantic":[43],"grounding":[45],"gaps,":[46,55],"leaving":[47],"models":[48],"vulnerable":[49],"hallucinations.":[51],"To":[52],"bridge":[53],"these":[54],"we":[56],"propose":[57],"EC-RAG,":[58],"an":[59,69],"Evidence-Centric":[60],"Active":[61,75],"RAG":[62],"framework":[63],"that":[64,107],"shifts":[65],"paradigm":[67],"\"seek-and-verify\"":[71],"cycle":[72],"integrating":[74],"Evidence-Driven":[76],"Retrieval":[77],"(AEDR)":[78],"for":[79,86],"precise":[80],"hypothesis":[81],"formation,":[82],"Visual-Consistency":[83],"Verification":[84],"(VCV)":[85],"pixel-level":[87],"filtering,":[88],"Dual-Source":[90],"Evidence":[91],"Fusion":[92],"(DSEF).":[93],"Extensive":[94],"validation":[95],"comprehensive":[98],"OmniMedVQA":[99],"benchmark":[100],"three":[102],"report":[103],"generation":[104],"datasets":[105],"demonstrates":[106],"our":[108],"method":[109],"significantly":[110],"enhances":[111],"factual":[112],"consistency,":[113],"achieving":[114],"7.77%":[116],"improvement":[117],"in":[118,140,144],"ROUGE-L":[119],"large-scale":[122],"MIMIC-CXR":[123],"dataset":[124],"securing":[126],"robust":[127],"generalization":[128],"across":[129],"12":[130],"diverse":[131],"imaging":[132],"modalities,":[133],"with":[134],"specific":[135],"accuracy":[136],"gains":[137],"8.93%":[139],"Ultrasound":[141],"5.82%":[143],"Computed":[145],"Tomography":[146],"tasks.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-16T00:00:00"}