{"id":"https://openalex.org/W7204452208","doi":"https://doi.org/10.48550/arxiv.2608.25986","title":"Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs","display_name":"Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204452208","doi":"https://doi.org/10.48550/arxiv.2608.25986"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.25986","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25986","pdf_url":"https://arxiv.org/pdf/2608.25986","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.25986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134410539","display_name":"Zongyu Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Zongyu","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102784377","display_name":"Yilong Wang","orcid":"https://orcid.org/0009-0009-2851-3055","observed_orcids":["https://orcid.org/0009-0009-2851-3055"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Yilong","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126971052","display_name":"Xiaochen Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xiaochen","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039804358","display_name":"Minhua Lin","orcid":"https://orcid.org/0000-0003-1591-7172","observed_orcids":["https://orcid.org/0000-0003-1591-7172"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Minhua","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148419427","display_name":"Zhichao Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Zhichao","raw_affiliation_strings":["University of Utah Salt Lake City , Utah , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah Salt Lake City , Utah , USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001030192","display_name":"Fenglong Ma","orcid":"https://orcid.org/0000-0002-4999-0303","observed_orcids":["https://orcid.org/0000-0002-4999-0303"]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ma, Fenglong","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144389954","display_name":"Xiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Xiang","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137169168","display_name":"Suhang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Suhang","raw_affiliation_strings":["The Pennsylvania State University University Park , Pennsylvania , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University University Park , Pennsylvania , USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0010000000474974513,"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/T11273","display_name":"Advanced Graph Neural Networks","score":9.999999747378752e-05,"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/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9639999866485596},{"id":"https://openalex.org/keywords/multimodal-knowledge-graphs","display_name":"multimodal knowledge graphs","score":0.9399999976158142},{"id":"https://openalex.org/keywords/graphrag","display_name":"GraphRAG","score":0.8220000267028809},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9110000133514404},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.7269999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105000257492065},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.7039999961853027},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44999998807907104},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41339999437332153},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.27469998598098755},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.25986","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25986","pdf_url":"https://arxiv.org/pdf/2608.25986","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.25986","doi":"https://doi.org/10.48550/arxiv.2608.25986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.25986","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.25986","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.25986","pdf_url":"https://arxiv.org/pdf/2608.25986","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5653452277183533,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204452208.pdf","grobid_xml":"https://content.openalex.org/works/W7204452208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7152019015","https://openalex.org/W7117146243","https://openalex.org/W7117339518","https://openalex.org/W7077051762","https://openalex.org/W7118018001","https://openalex.org/W7163007970","https://openalex.org/W7117271432","https://openalex.org/W7214724280","https://openalex.org/W7213277289","https://openalex.org/W7129042046"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"is":[3,95,221],"widely":[4],"used":[5,97],"to":[6,30,58,98,141,176,201,227],"mitigate":[7],"hallucination":[8],"issues":[9],"in":[10,79,223],"large":[11,17],"language":[12,18],"models":[13,19],"(LLMs)":[14],"and":[15,106,118,159],"multimodal":[16,45,108,123,144],"(MLLMs).":[20],"In":[21],"particular,":[22],"knowledge":[23,29,46,50,60,109],"graph":[24],"(KG)-based":[25],"RAG":[26,57,72,230,238],"leverages":[27],"structured":[28],"provide":[31],"(M)LLMs":[32],"with":[33,152],"high-quality":[34],"external":[35],"information.":[36],"Building":[37],"on":[38,213],"these":[39],"works,":[40],"recent":[41],"studies":[42],"have":[43],"explored":[44],"graphs":[47],"(MMKGs)":[48],"as":[49],"bases":[51],"for":[52,135,195],"GraphRAG.":[53,145],"This":[54,111],"enables":[55],"Graph":[56],"integrate":[59],"across":[61,235],"multiple":[62],"modalities,":[63],"thereby":[64],"further":[65,190],"enhancing":[66],"its":[67,233,241],"performance.":[68,125,231],"However,":[69],"existing":[70],"MMKG-based":[71,229,237],"methods":[73,239],"generally":[74],"follow":[75],"a":[76,91,99,113,132,137,183,192],"common":[77],"pipeline":[78],"which":[80,120],"different":[81,207,236],"modalities":[82],"are":[83,173],"largely":[84],"processed":[85],"independently":[86],"before":[87],"being":[88],"fusion.":[89,110],"As":[90],"result,":[92],"textual":[93,154],"context":[94,155,163,181],"only":[96],"limited":[100],"extent":[101],"during":[102],"visual":[103],"information":[104,205,226],"extraction":[105],"subsequent":[107],"brings":[112],"semantic":[114],"gap":[115],"between":[116],"images":[117],"text":[119,168],"limits":[121],"the":[122,166,177,186,196,214],"GraphRAG":[124],"To":[126],"address":[127],"this":[128],"issue,":[129],"we":[130],"propose":[131],"novel":[133],"framework":[134],"constructing":[136],"Context-Enhanced":[138],"MMKG":[139],"(CEMMKG)":[140],"better":[142],"support":[143],"The":[146],"proposed":[147],"CEMMKG":[148,220],"enriches":[149],"each":[150],"image":[151],"complementary":[153],"at":[156,206],"both":[157],"local":[158,197],"global":[160,180],"scopes.":[161],"Local":[162],"goes":[164],"beyond":[165],"surrounding":[167],"by":[169],"incorporating":[170],"sentences":[171],"that":[172,219],"semantically":[174,203],"related":[175],"image,":[178],"while":[179],"provides":[182],"summary":[184],"of":[185,209],"entire":[187],"passage.":[188],"We":[189],"introduce":[191],"multi-granularity":[193],"design":[194],"context,":[198],"allowing":[199],"it":[200],"capture":[202],"relevant":[204],"levels":[208],"detail.":[210],"Extensive":[211],"experiments":[212],"selected":[215],"vision-centric":[216],"dataset":[217],"validate":[218],"effective":[222],"leveraging":[224],"contextual":[225],"improve":[228],"Moreover,":[232],"effectiveness":[234],"demonstrates":[240],"broad":[242],"applicability.":[243]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}