{"id":"https://openalex.org/W4415873442","doi":"https://doi.org/10.18653/v1/2026.acl-long.204","title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","display_name":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415873442","doi":"https://doi.org/10.18653/v1/2026.acl-long.204"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.204","pdf_url":"https://aclanthology.org/2026.acl-long.204.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.204.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sensen Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sensen Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016283346","display_name":"Shanshan Zhao","orcid":"https://orcid.org/0000-0001-5476-6894"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanshan Zhao","raw_affiliation_strings":["Alibaba Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020776902","display_name":"Xu Jiang","orcid":"https://orcid.org/0000-0001-7324-7125"},"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":"Xu Jiang","raw_affiliation_strings":["Tsinghua University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017333360","display_name":"Lunhao Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lunhao Duan","raw_affiliation_strings":["Wuhan University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University ,","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120249509","display_name":"Yong Xien Chng","orcid":null},"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":"Yong Xien Chng","raw_affiliation_strings":["Tsinghua University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University ,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638352","display_name":"Qing-Guo Chen","orcid":"https://orcid.org/0000-0001-8938-5776"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing-Guo Chen","raw_affiliation_strings":["Alibaba Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110283717","display_name":"Weihua Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weihua Luo","raw_affiliation_strings":["Alibaba Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103619995","display_name":"Kaifu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaifu Zhang","raw_affiliation_strings":["Alibaba Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072209031","display_name":"Jia-Wang Bian","orcid":"https://orcid.org/0000-0003-2046-3363"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jia-Wang Bian","raw_affiliation_strings":["Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102023771","display_name":"Mingming Gong","orcid":"https://orcid.org/0000-0001-7147-5589"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingming Gong","raw_affiliation_strings":["University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01352601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4458","last_page":"4489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.5056999921798706,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.5056999921798706,"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":0.13189999759197235,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.1177000030875206,"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/key","display_name":"Key (lock)","score":0.5342000126838684},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4948999881744385},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.41830000281333923},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3528999984264374},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.3386000096797943},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.3111000061035156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6531000137329102},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6004999876022339},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.204","pdf_url":"https://aclanthology.org/2026.acl-long.204.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.15253","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.15253","pdf_url":"https://arxiv.org/pdf/2510.15253","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218861","is_oa":true,"landing_page_url":"https://aclanthology.org/2026.acl-long.204/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.2510.15253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.15253","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:10.18653/v1/2026.acl-long.204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.204","pdf_url":"https://aclanthology.org/2026.acl-long.204.pdf","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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415873442.pdf","grobid_xml":"https://content.openalex.org/works/W4415873442.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sensen":[0],"Gao,":[1],"Shanshan":[2],"Zhao,":[3],"Xu":[4],"Jiang,":[5],"Lunhao":[6],"Duan,":[7],"Yong":[8],"Xien":[9],"Chng,":[10],"Qing-Guo":[11],"Chen,":[12],"Weihua":[13],"Luo,":[14],"Kaifu":[15],"Zhang,":[16],"Jia-Wang":[17],"Bian,":[18],"Mingming":[19],"Gong.":[20],"Proceedings":[21],"of":[22,27],"the":[23,28],"64th":[24],"Annual":[25],"Meeting":[26],"Association":[29],"for":[30],"Computational":[31],"Linguistics":[32],"(Volume":[33],"1:":[34],"Long":[35],"Papers).":[36],"2026.":[37]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-21T00:00:00"}
