{"id":"https://openalex.org/W4415540505","doi":"https://doi.org/10.1145/3746027.3755625","title":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","display_name":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540505","doi":"https://doi.org/10.1145/3746027.3755625"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106671208","display_name":"Zhenghao Liu","orcid":"https://orcid.org/0000-0003-0083-3224"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Liu","raw_affiliation_strings":["Northeastern University, China, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-0083-3224","affiliations":[{"raw_affiliation_string":"Northeastern University, China, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111544541","display_name":"Xingsheng Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingsheng Zhu","raw_affiliation_strings":["Northeastern University, China, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0005-3777-7643","affiliations":[{"raw_affiliation_string":"Northeastern University, China, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042268955","display_name":"Tianshuo Zhou","orcid":"https://orcid.org/0009-0001-4234-9345"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshuo Zhou","raw_affiliation_strings":["Northeastern University, China, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0001-4234-9345","affiliations":[{"raw_affiliation_string":"Northeastern University, China, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyi Zhang","orcid":"https://orcid.org/0009-0007-6982-8059"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["Northeastern University, China, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0007-6982-8059","affiliations":[{"raw_affiliation_string":"Northeastern University, China, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026595284","display_name":"Xiaoyuan Yi","orcid":"https://orcid.org/0000-0003-2710-1613"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yi","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2710-1613","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034266748","display_name":"Yukun Yan","orcid":"https://orcid.org/0000-0003-2421-7098"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Yan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2421-7098","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, China, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-3171-8889","affiliations":[{"raw_affiliation_string":"Northeastern University, China, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6011-6115","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4817","last_page":"4826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9944000244140625,"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":0.9915000200271606,"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/benchmarking","display_name":"Benchmarking","score":0.7651000022888184},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7218999862670898},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5788000226020813},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5764999985694885},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.536300003528595},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5063999891281128},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42480000853538513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251000046730042},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7651000022888184},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7218999862670898},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5063999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4858983092","display_name":null,"funder_award_id":"62461146205","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2561715562","https://openalex.org/W2966317026","https://openalex.org/W4252076394","https://openalex.org/W4312643954","https://openalex.org/W4327810158","https://openalex.org/W4386065803","https://openalex.org/W4402727536","https://openalex.org/W4402916777"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,52,113,140,147],"rapid":[2],"advancement":[3],"of":[4,54,117,142,149],"Multi-modal":[5,55],"Large":[6,56],"Language":[7,57],"Models":[8,58],"(MLLMs),":[9],"their":[10,22],"capability":[11],"in":[12,29,59,86],"understanding":[13],"both":[14],"images":[15],"and":[16,79,102,159,163,169],"text":[17],"has":[18],"greatly":[19],"improved.":[20],"However,":[21],"potential":[23],"for":[24,108],"leveraging":[25,60],"multi-modal":[26,63,73,76,99,135],"contextual":[27,106],"information":[28,96],"Retrieval-Augmented":[30,44,123],"Generation":[31,45],"(RAG)":[32],"remains":[33],"largely":[34],"underexplored.":[35],"To":[36,111],"address":[37],"this":[38,40],"gap,":[39],"paper":[41],"introduces":[42],"Multi-Modal":[43,122],"(M2RAG),":[46],"a":[47,98],"benchmark":[48,67],"designed":[49],"to":[50,93],"evaluate":[51],"effectiveness":[53,141],"knowledge":[61],"from":[62,97],"retrieval":[64],"documents.":[65],"The":[66],"comprises":[68],"four":[69],"tasks:":[70],"image":[71,80],"captioning,":[72],"question":[74],"answering,":[75],"fact":[77],"verification,":[78],"reranking.":[81],"All":[82,167],"tasks":[83],"are":[84,171],"set":[85],"an":[87,127],"open-domain":[88],"setting,":[89],"requiring":[90],"RAG":[91,109,154],"models":[92],"retrieve":[94],"query-relevant":[95],"document":[100],"collection":[101],"use":[103],"it":[104],"as":[105],"input":[107],"modeling.":[110],"enhance":[112],"context":[114],"utilization":[115],"capabilities":[116],"MLLMs,":[118],"we":[119],"also":[120],"introduce":[121],"Instruction":[124],"Tuning":[125],"(MM-RAIT),":[126],"instruction":[128],"tuning":[129],"method":[130],"that":[131],"optimizes":[132],"MLLMs":[133],"within":[134],"contexts.":[136],"Our":[137],"experiments":[138],"demonstrate":[139],"MM-RAIT":[143],"by":[144,152],"significantly":[145],"improving":[146],"quality":[148],"responses":[150],"generated":[151],"different":[153],"models,":[155],"outperforming":[156],"MiniCPM-V":[157],"2.6":[158],"Qwen2-VL":[160],"with":[161],"34%":[162],"33%":[164],"gains,":[165],"respectively.":[166],"data":[168],"code":[170],"available":[172],"at":[173],"https://github.com/NEUIR/M2RAG.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-25T00:00:00"}