{"id":"https://openalex.org/W7157249900","doi":"https://doi.org/10.48550/arxiv.2604.24564","title":"MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG","display_name":"MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7157249900","doi":"https://doi.org/10.48550/arxiv.2604.24564"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24564","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.24564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134770534","display_name":"Xihang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134782789","display_name":"Zihan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134802508","display_name":"Chengkai Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chengkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134791357","display_name":"Quan Z. Sheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng, Quan Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134750556","display_name":"Lina Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Lina","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":false,"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/T10028","display_name":"Topic Modeling","score":0.6333000063896179,"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/T10028","display_name":"Topic Modeling","score":0.6333000063896179,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2272000014781952,"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":0.021299999207258224,"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/metric","display_name":"Metric (unit)","score":0.531000018119812},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5212000012397766},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.48080000281333923},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48010000586509705},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4523000121116638},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4507000148296356},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4438000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504999756813049},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48080000281333923},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4142000079154968},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25859999656677246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24564","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.24564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24564","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8265146613121033,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,8],"Retrieval-Augmented":[1],"Generation":[2],"(MRAG)":[3],"addresses":[4],"key":[5],"limitations":[6],"of":[7,35,58,77,100,124,148],"Large":[9],"Language":[10],"Models":[11],"(MLLMs),":[12],"such":[13],"as":[14],"hallucination":[15],"and":[16,145,164],"outdated":[17],"knowledge.":[18],"However,":[19],"current":[20],"MRAG":[21],"systems":[22],"struggle":[23],"to":[24,53,116],"distinguish":[25],"whether":[26],"retrieved":[27,78,118],"multimodal":[28,59,114,146],"data":[29],"truly":[30],"supports":[31],"the":[32,55,75,97,101,121,125,143,154],"semantic":[33,98,122,134],"core":[34,99],"an":[36],"answer":[37],"or":[38],"merely":[39],"provides":[40],"superficial":[41],"relevance.":[42],"Existing":[43],"metrics":[44],"often":[45],"rely":[46],"on":[47,90,104,133,153],"heuristic":[48],"position-based":[49],"confidence,":[50],"which":[51],"fails":[52],"capture":[54,96],"informational":[56],"density":[57],"entities.":[60],"To":[61],"address":[62],"this,":[63],"we":[64,106],"propose":[65],"Multi-modal":[66],"Evidence":[67],"Grounding":[68],"(MEG),":[69],"a":[70,109,113],"semantic-aware":[71],"metric":[72],"that":[73,94,111,158],"quantifies":[74],"contribution":[76],"evidence.":[79],"Unlike":[80],"standard":[81],"confidence":[82],"measures,":[83],"MEG":[84],"utilizes":[85],"Semantic":[86],"Certainty":[87],"Anchoring,":[88],"focusing":[89],"high-IDF":[91],"information-bearing":[92],"tokens":[93],"better":[95],"answer.":[102],"Building":[103],"MEG,":[105],"introduce":[107],"MEG-RAG,":[108],"framework":[110],"trains":[112],"reranker":[115],"align":[117],"evidence":[119],"with":[120],"anchors":[123],"ground":[126],"truth.":[127],"By":[128],"prioritizing":[129],"high-value":[130],"content":[131],"based":[132],"grounding":[135],"rather":[136],"than":[137],"token":[138],"probability":[139],"distributions,":[140],"MEG-RAG":[141,159],"improves":[142],"accuracy":[144],"consistency":[147],"generated":[149],"outputs.":[150],"Extensive":[151],"experiments":[152],"M$^2$RAG":[155],"benchmark":[156],"show":[157],"consistently":[160],"outperforms":[161],"strong":[162],"baselines":[163],"demonstrates":[165],"robust":[166],"generalization":[167],"across":[168],"different":[169],"teacher":[170],"models.":[171]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-29T00:00:00"}