{"id":"https://openalex.org/W7138463078","doi":"https://doi.org/10.1609/aaai.v40i4.37216","title":"Enhancing Retrieval-Augmented Large Vision Language Models via Knowledge Conflict Mitigation","display_name":"Enhancing Retrieval-Augmented Large Vision Language Models via Knowledge Conflict Mitigation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138463078","doi":"https://doi.org/10.1609/aaai.v40i4.37216"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i4.37216","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37216","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37216/41178","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37216/41178","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129705955","display_name":"Wenbin An","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin An","raw_affiliation_strings":["Xi'an Jiaotong University\nNational Engineering Laboratory for Big Data Analytics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University\nNational Engineering Laboratory for Big Data Analytics","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051595025","display_name":"Jiahao Nie","orcid":"https://orcid.org/0000-0002-1474-1817"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiahao Nie","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129675249","display_name":"Feng Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Tian","raw_affiliation_strings":["Xi'an Jiaotong University\nNational Engineering Laboratory for Big Data Analytics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University\nNational Engineering Laboratory for Big Data Analytics","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061275080","display_name":"Mingxiang Cai","orcid":"https://orcid.org/0000-0001-6816-5192"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxiang Cai","raw_affiliation_strings":["Lenovo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo Research","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129716271","display_name":"Yaqiang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqiang Wu","raw_affiliation_strings":["Lenovo Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo Research","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712599","display_name":"Xiaoqin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Zhang","raw_affiliation_strings":["Zhejiang University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129742453","display_name":"Shijian Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shijian Lu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75498575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"2318","last_page":"2326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8503000140190125,"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":0.8503000140190125,"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/T10028","display_name":"Topic Modeling","score":0.06509999930858612,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.015200000256299973,"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/context","display_name":"Context (archaeology)","score":0.6705999970436096},{"id":"https://openalex.org/keywords/contextual-design","display_name":"Contextual design","score":0.5716999769210815},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5149999856948853},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5005000233650208},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/knowledge-flow","display_name":"Knowledge flow","score":0.4300999939441681},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42719998955726624},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4187999963760376},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947000026702881},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6705999970436096},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.5716999769210815},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5005000233650208},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C2984563274","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge flow","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.39320001006126404},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.38999998569488525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889000117778778},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C52085439","wikidata":"https://www.wikidata.org/wiki/Q5165173","display_name":"Context analysis","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C135355979","wikidata":"https://www.wikidata.org/wiki/Q5165193","display_name":"Contextual inquiry","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C56289545","wikidata":"https://www.wikidata.org/wiki/Q6423376","display_name":"Knowledge integration","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2522999942302704},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i4.37216","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37216","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37216/41178","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37216","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37216","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37216","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37216/41178","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3334390406","display_name":null,"funder_award_id":"62293551","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4283126175","display_name":null,"funder_award_id":"62277042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5037207851","display_name":null,"funder_award_id":"62377038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G833875181","display_name":null,"funder_award_id":"62177038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321169","display_name":"Xi\u2019an Jiaotong University","ror":"https://ror.org/017zhmm22"},{"id":"https://openalex.org/F4320321174","display_name":"Housing and Building National Research Center","ror":"https://ror.org/03562m240"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138463078.pdf","grobid_xml":"https://content.openalex.org/works/W7138463078.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Retrieval-Augmented":[1],"Generation":[2],"(MRAG)":[3],"has":[4],"recently":[5],"been":[6],"explored":[7],"to":[8,23,50,109,159],"empower":[9],"Large":[10],"Vision":[11],"Language":[12],"Models":[13],"(LVLMs)":[14],"with":[15,44,114],"more":[16,79,135],"comprehensive":[17],"and":[18,28,53,66,120,133,168],"up-to-date":[19],"contextual":[20,38,85,112,139],"knowledge,":[21,48,129],"aiming":[22],"compensate":[24],"for":[25,78],"their":[26],"limited":[27],"coarse-grained":[29,127],"parametric":[30,47,128],"knowledge":[31,39,51,73,86,113],"in":[32],"knowledge-intensive":[33],"tasks.":[34],"However,":[35],"the":[36,90,144,148,160,174],"retrieved":[37],"is":[40],"usually":[41],"not":[42],"aligned":[43],"LVLMs\u2019":[45],"internal":[46],"leading":[49],"conflicts":[52,74],"further":[54],"unreliable":[55],"responses.":[56,82],"To":[57],"tackle":[58],"this":[59],"issue,":[60],"we":[61],"design":[62],"KCM,":[63],"a":[64],"training-free":[65],"plug-and-play":[67],"framework":[68],"that":[69,125,171],"can":[70],"effectively":[71],"mitigate":[72],"while":[75],"incorporating":[76],"MRAG":[77],"accurate":[80],"LVLM":[81,91,123],"KCM":[83,98,118,142,172],"enhances":[84],"utilization":[87],"by":[88,151,177],"modifying":[89],"architecture":[92],"from":[93,147],"three":[94],"key":[95],"perspectives.":[96],"First,":[97],"adaptively":[99],"adjusts":[100],"attention":[101,105],"distributions":[102],"among":[103],"multiple":[104,166],"heads,":[106],"encouraging":[107],"LVLMs":[108,167],"focus":[110],"on":[111],"reduced":[115],"distraction.":[116],"Second,":[117],"identifies":[119],"prunes":[121],"knowledge-centric":[122],"neurons":[124],"encode":[126],"thereby":[130],"suppressing":[131],"interferences":[132],"enabling":[134],"effective":[136],"integration":[137],"of":[138],"knowledge.":[140],"Third,":[141],"amplifies":[143],"information":[145],"flow":[146],"input":[149],"context":[150,154],"injecting":[152],"supplementary":[153],"logits,":[155],"reinforcing":[156],"its":[157],"contribution":[158],"final":[161],"output.":[162],"Extensive":[163],"experiments":[164],"over":[165],"benchmarks":[169],"show":[170],"outperforms":[173],"state-of-the-art":[175],"consistently":[176],"large":[178],"margins,":[179],"incurring":[180],"neither":[181],"extra":[182],"training":[183],"nor":[184],"external":[185],"tools.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}