{"id":"https://openalex.org/W4412889669","doi":"https://doi.org/10.18653/v1/2025.acl-long.1583","title":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","display_name":"CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889669","doi":"https://doi.org/10.18653/v1/2025.acl-long.1583"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1583","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1583","pdf_url":"https://aclanthology.org/2025.acl-long.1583.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1583.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059468080","display_name":"Yang Tian","orcid":"https://orcid.org/0000-0002-9293-5852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032283270","display_name":"Fan Liu","orcid":"https://orcid.org/0000-0001-7118-4829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639611","display_name":"Jingyuan Zhang","orcid":"https://orcid.org/0009-0009-6242-2106"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyuan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181836","display_name":"V. W.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V. W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069741536","display_name":"Yupeng Hu","orcid":"https://orcid.org/0000-0002-7358-7426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupeng Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Nie","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":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32967","last_page":"32982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9580000042915344,"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/T12031","display_name":"Speech and dialogue systems","score":0.9580000042915344,"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/core","display_name":"Core (optical fiber)","score":0.644221842288971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178619265556335},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11627471446990967}],"concepts":[{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.644221842288971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178619265556335},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11627471446990967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1583","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1583","pdf_url":"https://aclanthology.org/2025.acl-long.1583.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1583","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1583","pdf_url":"https://aclanthology.org/2025.acl-long.1583.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G3981135610","display_name":null,"funder_award_id":"62276155","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889669.pdf","grobid_xml":"https://content.openalex.org/works/W4412889669.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/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Multimodal":[0,9],"Retrieval-Augmented":[1],"Generation":[2],"(MMRAG)":[3],"has":[4],"been":[5],"introduced":[6],"to":[7,110],"enhance":[8],"Large":[10],"Language":[11],"Models":[12],"by":[13],"incorporating":[14],"externally":[15],"retrieved":[16,33],"multimodal":[17,96,123],"knowledge,":[18,90],"but":[19],"it":[20,82],"introduces":[21],"two":[22],"challenges:":[23],"Parametric-Retrieved":[24],"Knowledge":[25,42],"Inconsistency":[26,43],"(PRKI),":[27],"where":[28,45],"discrepancies":[29],"between":[30,47],"parametric":[31,89],"and":[32,40,49,106,125,143,149,154],"knowledge":[34,61,76,120],"create":[35],"uncertainty":[36],"in":[37],"determining":[38],"reliability,":[39],"Visual-Textual":[41],"(VTKI),":[44],"misalignment":[46],"visual":[48],"textual":[50],"sources":[51],"disrupts":[52],"entity":[53],"representation.To":[54],"address":[55],"these":[56],"challenges,":[57],"we":[58],"propose":[59],"Cross-source":[60],"Reconciliation":[62],"for":[63],"MultiModal":[64],"RAG":[65],"(CoRe-MMRAG),":[66],"a":[67,79,112,115],"novel":[68],"end-to-end":[69],"framework":[70],"that":[71,133],"effectively":[72],"reconciles":[73],"inconsistencies":[74],"across":[75],"sources.CoRe-MMRAG":[77],"follows":[78],"four-stage":[80],"pipeline:":[81],"first":[83],"generates":[84,102],"an":[85,103],"internal":[86],"response":[87],"from":[88],"then":[91],"selects":[92],"the":[93],"most":[94],"relevant":[95],"evidence":[97],"via":[98],"joint":[99],"similarity":[100],"assessment,":[101],"external":[104],"response,":[105],"finally":[107],"integrates":[108],"both":[109],"produce":[111],"reliable":[113],"answer.Additionally,":[114],"specialized":[116],"training":[117],"paradigm":[118],"enhances":[119],"source":[121],"discrimination,":[122],"integration,":[124],"unified":[126],"answer":[127],"generation.Experiments":[128],"on":[129,147],"KB-VQA":[130],"benchmarks":[131],"show":[132],"CoRe-MMRAG":[134],"achieves":[135],"substantial":[136],"improvements":[137],"over":[138],"baseline":[139],"methods,":[140],"achieving":[141],"5.6%":[142],"9.3%":[144],"performance":[145],"gains":[146],"InfoSeek":[148],"Encyclopedic-VQA,":[150],"respectively.We":[151],"release":[152],"code":[153],"data":[155],"at":[156],"https://github.com/TyangJN/CoRe-MMRAG.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}