{"id":"https://openalex.org/W4412377067","doi":"https://doi.org/10.1145/3726302.3730288","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","display_name":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377067","doi":"https://doi.org/10.1145/3726302.3730288"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730288","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730288","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730288","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109584477","display_name":"Qinhan Yu","orcid":"https://orcid.org/0009-0004-0445-0786"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinhan Yu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0445-0786","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyou Xiao","orcid":"https://orcid.org/0009-0002-8919-0113"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyou Xiao","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-8919-0113","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Binghui Li","orcid":"https://orcid.org/0009-0004-3506-3770"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binghui Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3506-3770","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377090","display_name":"Zhengren Wang","orcid":"https://orcid.org/0000-0003-3541-9322"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengren Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3541-9322","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025013542","display_name":"Chong Chen","orcid":"https://orcid.org/0000-0003-1417-2295"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Chen","raw_affiliation_strings":["Huawei Cloud BU, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1417-2295","affiliations":[{"raw_affiliation_string":"Huawei Cloud BU, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008772211","display_name":"Wentao Zhang","orcid":"https://orcid.org/0000-0002-7532-5550"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7532-5550","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109584477"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":3.3997,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9280708,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3616","last_page":"3626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8140205144882202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733521580696106},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.5884115695953369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43731772899627686},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4234354496002197},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32850271463394165},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05395665764808655}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8140205144882202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733521580696106},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.5884115695953369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43731772899627686},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4234354496002197},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32850271463394165},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05395665764808655},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730288","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730288","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730288","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730288","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7808423170","display_name":null,"funder_award_id":"92470121, 62402016","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377067.pdf","grobid_xml":"https://content.openalex.org/works/W4412377067.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2143996849","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2947312908","https://openalex.org/W2963339397","https://openalex.org/W2963748441","https://openalex.org/W3156892778","https://openalex.org/W4233756358","https://openalex.org/W4312846625","https://openalex.org/W4386057720","https://openalex.org/W6600862597","https://openalex.org/W6681272064"],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2968405290","https://openalex.org/W2960696728","https://openalex.org/W2114040463","https://openalex.org/W2053633997"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,33,46,62,182],"Retrieval-Augmented":[3,35,57],"Generation":[4,36,59],"(RAG)":[5],"have":[6],"significantly":[7],"improved":[8],"response":[9],"accuracy":[10],"and":[11,74,121,130,136,144,169,191,207],"relevance":[12],"by":[13],"incorporating":[14],"external":[15],"knowledge":[16],"into":[17],"Large":[18],"Language":[19],"Models":[20],"(LLMs).":[21],"However,":[22],"existing":[23],"RAG":[24],"methods":[25],"primarily":[26],"focus":[27],"on":[28],"generating":[29,47],"text-only":[30],"answers,":[31],"even":[32],"Multimodal":[34,56,58],"(MRAG)":[37],"scenarios,":[38,147],"where":[39],"multimodal":[40,68,79,193,203],"elements":[41],"are":[42,216],"retrieved":[43],"to":[44,66,87,201],"assist":[45],"text":[48,73],"answers.":[49],"To":[50,104,157],"address":[51],"this,":[52],"we":[53,64,108,187],"introduce":[54],"the":[55,78,154,177,183],"(MRAMG)":[60],"task,":[61,90],"which":[63],"aim":[65],"generate":[67,202],"answers":[69],"that":[70,197],"combine":[71],"both":[72,167],"images,":[75,120],"fully":[76],"leveraging":[77],"data":[80],"within":[81],"a":[82,91,95,111,149,163,173],"corpus.":[83],"Despite":[84],"growing":[85],"attention":[86],"this":[88,106],"challenging":[89],"notable":[92],"lack":[93],"of":[94,166,176,179],"comprehensive":[96,164],"benchmark":[97,115],"persists":[98],"for":[99,152,211],"effectively":[100],"evaluating":[101,153],"its":[102],"performance.":[103],"bridge":[105],"gap,":[107],"provide":[109],"MRAMG-Bench,":[110],"meticulously":[112],"curated,":[113],"human-annotated":[114],"comprising":[116],"4,346":[117],"documents,":[118],"14,190":[119],"4,800":[122],"QA":[123],"pairs,":[124],"distributed":[125],"across":[126],"six":[127],"distinct":[128],"datasets":[129,139,206],"spanning":[131],"three":[132],"domains:":[133],"Web,":[134],"Academia,":[135],"Lifestyle.":[137],"The":[138],"incorporate":[140],"diverse":[141],"difficulty":[142],"levels":[143],"complex":[145],"multi-image":[146],"providing":[148],"robust":[150],"foundation":[151],"MRAMG":[155,184],"task.":[156,185],"facilitate":[158],"rigorous":[159],"evaluation,":[160],"MRAMG-Bench":[161],"incorporates":[162],"suite":[165],"statistical":[168],"LLM-based":[170],"metrics,":[171],"enabling":[172],"thorough":[174],"analysis":[175],"performance":[178],"generative":[180,214],"models":[181,215],"Additionally,":[186],"propose":[188],"an":[189],"efficient":[190],"flexible":[192],"answer":[194],"generation":[195],"framework":[196],"can":[198],"leverage":[199],"LLMs/MLLMs":[200],"responses.":[204],"Our":[205],"complete":[208],"evaluation":[209],"results":[210],"11":[212],"popular":[213],"available":[217],"at":[218],"https://github.com/MRAMG-Bench/MRAMG.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}