{"id":"https://openalex.org/W4412889737","doi":"https://doi.org/10.18653/v1/2025.acl-long.1456","title":"VISA: Retrieval Augmented Generation with Visual Source Attribution","display_name":"VISA: Retrieval Augmented Generation with Visual Source Attribution","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889737","doi":"https://doi.org/10.18653/v1/2025.acl-long.1456"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1456","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1456","pdf_url":"https://aclanthology.org/2025.acl-long.1456.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1456.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021623012","display_name":"Xueguang Ma","orcid":"https://orcid.org/0000-0003-3430-4910"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueguang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012958162","display_name":"Shengyao Zhuang","orcid":"https://orcid.org/0000-0002-6711-0955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyao Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087733750","display_name":"Bevan Koopman","orcid":"https://orcid.org/0000-0001-5577-3391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bevan Koopman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063070498","display_name":"Wenhu Chen","orcid":"https://orcid.org/0000-0002-4375-8466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimmy Lin","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":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30154","last_page":"30169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9426000118255615,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9426000118255615,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9143999814987183,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9110999703407288,"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/computer-science","display_name":"Computer science","score":0.6492592096328735},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.5558041930198669},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42047318816185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3683202862739563},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1334424912929535},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.04651671648025513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492592096328735},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.5558041930198669},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42047318816185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3683202862739563},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1334424912929535},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.04651671648025513}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1456","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1456","pdf_url":"https://aclanthology.org/2025.acl-long.1456.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1456","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1456","pdf_url":"https://aclanthology.org/2025.acl-long.1456.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889737.pdf","grobid_xml":"https://content.openalex.org/works/W4412889737.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2035546108","https://openalex.org/W2376361520","https://openalex.org/W2133328864","https://openalex.org/W2093949997","https://openalex.org/W2570200690","https://openalex.org/W2389726244","https://openalex.org/W3030478661"],"abstract_inverted_index":{"Generation":[0,45],"with":[1,46,58,80],"source":[2,60,121],"attribution":[3,122],"is":[4],"important":[5],"for":[6,29,119,133],"enhancing":[7],"the":[8,68,72,77,84,110,115,131],"verifiability":[9],"of":[10,117],"retrievalaugmented":[11],"generation":[12,57],"(RAG)":[13],"systems.However,":[14],"existing":[15],"approaches":[16],"in":[17,83],"RAG":[18],"primarily":[19],"link":[20],"generated":[21,78],"content":[22],"to":[23,31,109],"document-level":[24],"references,":[25],"making":[26],"it":[27],"challenging":[28],"users":[30],"locate":[32],"evidence":[33,69],"among":[34],"multiple":[35],"content-rich":[36],"retrieved":[37,85],"documents.To":[38],"address":[39],"this":[40],"challenge,":[41],"we":[42,91],"propose":[43],"Retrieval-Augmented":[44],"Visual":[47],"Source":[48],"Attribution":[49],"(VISA),":[50],"a":[51],"novel":[52],"approach":[53],"that":[54,75],"combines":[55],"answer":[56],"visual":[59,120],"attribution.Leveraging":[61],"large":[62],"vision-language":[63],"models":[64],"(VLMs),":[65],"VISA":[66,118],"identifies":[67],"and":[70,102,107],"highlights":[71],"exact":[73],"regions":[74],"support":[76],"answers":[79],"bounding":[81],"boxes":[82],"document":[86],"screenshots.To":[87],"evaluate":[88],"its":[89],"effectiveness,":[90],"curated":[92],"two":[93],"datasets:":[94],"Wiki-VISA,":[95],"based":[96],"on":[97,123],"crawled":[98],"Wikipedia":[99],"webpage":[100],"screenshots,":[101],"Paper-VISA,":[103],"derived":[104],"from":[105],"PubLayNet":[106],"tailored":[108],"medical":[111],"domain.Experimental":[112],"results":[113],"demonstrate":[114],"effectiveness":[116],"documents'":[124],"original":[125],"look,":[126],"as":[127,129],"well":[128],"highlighting":[130],"challenges":[132],"improvement.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
