{"id":"https://openalex.org/W7158032602","doi":"https://doi.org/10.1145/3805712.3809680","title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","display_name":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7158032602","doi":"https://doi.org/10.1145/3805712.3809680"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809680","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809680","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809680","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134857602","display_name":"Xu Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xu Yuan","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2822-9443","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134859592","display_name":"Liangbo Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liangbo Ning","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-6903-8996","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134847173","display_name":"Qingqing Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qingqing Ye","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1547-2847","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134841766","display_name":"Wenqi Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenqi Fan","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4049-1233","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134827746","display_name":"Qing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-3370-471X","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2274","last_page":"2285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9368000030517578,"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":0.9368000030517578,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03610000014305115,"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/T10028","display_name":"Topic Modeling","score":0.00860000029206276,"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/knowledge-graph","display_name":"Knowledge graph","score":0.507099986076355},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4643000066280365},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.38179999589920044},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37070000171661377},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3474000096321106},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3057999908924103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087999820709229},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2775966667","wikidata":"https://www.wikidata.org/wiki/Q6423384","display_name":"Knowledge modeling","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3809680","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809680","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.05318","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.05318","pdf_url":"https://arxiv.org/pdf/2508.05318","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809680","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809680","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4078110728","display_name":null,"funder_award_id":"P0048625","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G4152100473","display_name":null,"funder_award_id":"T43-513/23-N","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4230321938","display_name":null,"funder_award_id":"P0051361","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G528947399","display_name":null,"funder_award_id":"P0042693","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G8341220247","display_name":null,"funder_award_id":"72442017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320307285","display_name":"Impact Fund","ror":"https://ror.org/00jb20j87"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"has":[3,30],"emerged":[4],"as":[5,140],"an":[6],"effective":[7],"paradigm":[8],"for":[9,34,112,180],"expanding":[10],"the":[11,26,54],"knowledge":[12,23,58,82,142],"capacity":[13],"of":[14],"Multimodal":[15],"Large":[16],"Language":[17],"Models":[18],"(MLLMs)":[19],"by":[20],"incorporating":[21],"external":[22],"sources":[24],"into":[25,85],"generation":[27,91,106],"process,":[28],"and":[29,52,69,122,131,175],"been":[31],"widely":[32],"adopted":[33],"knowledge-based":[35,181],"Visual":[36],"Question":[37],"Answering":[38],"(VQA).":[39],"Despite":[40],"impressive":[41],"advancements,":[42],"vanilla":[43],"RAG-based":[44,86],"VQA":[45,87,114],"methods":[46],"that":[47,168],"rely":[48],"on":[49],"unstructured":[50],"documents":[51],"overlook":[53],"structural":[55],"relations":[56,132],"among":[57],"elements":[59],"frequently":[60],"introduce":[61],"irrelevant":[62],"or":[63],"misleading":[64],"content,":[65],"degrading":[66],"answer":[67],"accuracy":[68],"reliability.":[70],"To":[71,96],"overcome":[72],"these":[73],"challenges,":[74],"a":[75,103,145,151],"promising":[76],"solution":[77],"is":[78,155,185],"to":[79,125,157],"integrate":[80],"multimodal":[81,94,110,134,138,153],"graphs":[83],"(KGs)":[84],"frameworks,":[88],"thereby":[89],"enhancing":[90],"through":[92],"structured":[93,141],"knowledge.":[95],"this":[97,99],"end,":[98],"paper":[100],"proposes":[101],"mKG-RAG,":[102],"novel":[104],"retrieval-augmented":[105],"framework":[107],"built":[108],"upon":[109],"KGs":[111,139],"knowledge-intensive":[113],"tasks.":[115],"Specifically,":[116],"mKG-RAG":[117],"leverages":[118],"MLLM-driven":[119],"graph":[120],"extraction":[121],"vision-text":[123],"matching":[124],"distill":[126],"semantically":[127],"consistent,":[128],"modality-complementary":[129],"entities":[130],"from":[133],"documents,":[135],"constructing":[136],"high-quality":[137],"representations.":[143],"Furthermore,":[144],"dual-stage":[146],"retrieval":[147,159],"strategy":[148],"equipped":[149],"with":[150],"query-aware":[152],"retriever":[154],"introduced":[156],"improve":[158],"efficiency":[160],"while":[161],"progressively":[162],"refining":[163],"precision.":[164],"Comprehensive":[165],"experiments":[166],"demonstrate":[167],"our":[169],"approach":[170],"significantly":[171],"outperforms":[172],"existing":[173],"approaches":[174],"sets":[176],"new":[177],"state-of-the-art":[178],"results":[179],"VQA.":[182],"The":[183],"code":[184],"available":[186],"at":[187],"https://github.com/xandery-geek/mKG-RAG.":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-30T00:00:00"}