{"id":"https://openalex.org/W4415539505","doi":"https://doi.org/10.1145/3746027.3755390","title":"MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering","display_name":"MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539505","doi":"https://doi.org/10.1145/3746027.3755390"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755390","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755390","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102668182","display_name":"Hui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wu","raw_affiliation_strings":["Key Laboratory of Target Cognition and Application Technology(TCAT), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China and School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-5673-3729","affiliations":[{"raw_affiliation_string":"Key Laboratory of Target Cognition and Application Technology(TCAT), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China and School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoquan Zhai","orcid":"https://orcid.org/0009-0008-6991-9097"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoquan Zhai","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6991-9097","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348348","display_name":"Yuchen Li","orcid":"https://orcid.org/0000-0002-3869-7881"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3869-7881","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062665223","display_name":"Hengyi Cai","orcid":"https://orcid.org/0000-0002-7147-5666"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyi Cai","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7147-5666","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033044200","display_name":"Peirong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peirong Zhang","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4171-3234","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652602","display_name":"Yidan Zhang","orcid":"https://orcid.org/0000-0002-7466-0234"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Zhang","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7466-0234","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108670891","display_name":"Lei Wang","orcid":"https://orcid.org/0009-0007-2414-9642"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2414-9642","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010203885","display_name":"Chunle Wang","orcid":"https://orcid.org/0009-0004-2612-3364"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunle Wang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2612-3364","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006816662","display_name":"Yingyan Hou","orcid":"https://orcid.org/0000-0002-2789-8581"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingyan Hou","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2789-8581","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050255638","display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiqiang Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9212-1947","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0684-6205","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"4329","last_page":"4338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9965999722480774,"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7218999862670898},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5952000021934509},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.49810001254081726},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4916999936103821},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47769999504089355},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46070000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101999759674072},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7218999862670898},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6373999714851379},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.3596999943256378},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3755390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755390","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.16313","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.16313","pdf_url":"https://arxiv.org/pdf/2604.16313","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2604.16313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16313","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755390","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755390","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2997154779","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W4312233877","https://openalex.org/W4312643954","https://openalex.org/W4382202558","https://openalex.org/W4385237494","https://openalex.org/W4388778348","https://openalex.org/W4389518671","https://openalex.org/W4389518895","https://openalex.org/W4389520670","https://openalex.org/W4390873312","https://openalex.org/W4391376033","https://openalex.org/W4400526199","https://openalex.org/W4401042773","https://openalex.org/W4402670169","https://openalex.org/W4404351611","https://openalex.org/W4404781906"],"related_works":[],"abstract_inverted_index":{"Retrieval-based":[0],"multimodal":[1,17,33,141],"document":[2,47,103],"QA":[3,142],"aims":[4],"to":[5,32,61,63,86,112],"identify":[6],"and":[7,37,53,89,105,116,127,151],"integrate":[8],"relevant":[9,68],"information":[10],"from":[11,131],"visually":[12],"rich":[13],"documents":[14,34],"with":[15],"complex":[16],"structures.":[18],"While":[19],"retrieval-augmented":[20],"generation":[21,126],"(RAG)":[22],"has":[23],"shown":[24],"strong":[25],"performance":[26],"in":[27],"text-based":[28],"QA,":[29],"its":[30],"extensions":[31],"remain":[35],"underexplored":[36],"face":[38],"significant":[39],"limitations.":[40],"Specifically,":[41],"current":[42],"approaches":[43],"rely":[44],"on":[45,109,139],"query-agnostic":[46],"representations":[48,104],"that":[49,100,121,145],"overlook":[50],"salient":[51],"content":[52,130],"use":[54],"static":[55],"top-k":[56],"evidence":[57,123],"selection,":[58],"which":[59,82],"fails":[60],"adapt":[62],"the":[64,76],"uncertain":[65],"distribution":[66],"of":[67,93],"information.":[69],"To":[70],"address":[71],"these":[72],"limitations,":[73],"we":[74],"propose":[75],"Multimodal":[77],"Adaptive":[78],"Retrieval-Augmented":[79],"(MARA)":[80],"framework,":[81],"introduces":[83],"query-adaptive":[84],"mechanisms":[85],"both":[87],"retrieval":[88,114,149],"generation.":[90],"MARA":[91,146],"consists":[92],"two":[94],"components:":[95],"a":[96,117,135],"Query-Aligned":[97],"Region":[98],"Encoder":[99],"builds":[101],"multi-level":[102],"reweights":[106],"them":[107],"based":[108],"query":[110],"relevance":[111,150],"improve":[113],"precision;":[115],"Self-Reflective":[118],"Evidence":[119],"Controller":[120],"monitors":[122],"sufficiency":[124],"during":[125],"adaptively":[128],"incorporates":[129],"lower-ranked":[132],"sources":[133],"using":[134],"sliding-window":[136],"strategy.":[137],"Experiments":[138],"six":[140],"benchmarks":[143],"demonstrate":[144],"consistently":[147],"improves":[148],"answer":[152],"quality":[153],"over":[154],"existing":[155],"SOTA":[156],"method.":[157]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}