{"id":"https://openalex.org/W4411177432","doi":"https://doi.org/10.1145/3742434","title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","display_name":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4411177432","doi":"https://doi.org/10.1145/3742434"},"language":"en","primary_location":{"id":"doi:10.1145/3742434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3742434","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","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/A5065871371","display_name":"Xiaoye Qu","orcid":"https://orcid.org/0000-0002-4907-3978"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoye Qu","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032554701","display_name":"Qiyuan Chen","orcid":"https://orcid.org/0000-0002-2315-4972"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyuan Chen","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323842","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-4488-0102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044176278","display_name":"Jiashuo Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuo Sun","raw_affiliation_strings":["Xiamen University, Xiamen, China","Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078220957","display_name":"Daizong Liu","orcid":"https://orcid.org/0000-0001-8179-4508"},"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":"Daizong Liu","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008417257","display_name":"Jianfeng Dong","orcid":"https://orcid.org/0000-0001-5244-3274"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Dong","raw_affiliation_strings":["Zhejiang Gongshang University, Hangzhou, China","Zhejiang Gongshang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]},{"raw_affiliation_string":"Zhejiang Gongshang University, China","institution_ids":["https://openalex.org/I75059550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065871371"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":7.5072,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97272505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"21","issue":"9","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9894000291824341,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9843999743461609,"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":0.8687970638275146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4783322811126709},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4508386552333832},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44935205578804016},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.4223059415817261},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4123117923736572},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32566651701927185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687970638275146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4783322811126709},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4508386552333832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44935205578804016},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.4223059415817261},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4123117923736572},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32566651701927185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3742434","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2584637367","https://openalex.org/W2963518342","https://openalex.org/W4281560470","https://openalex.org/W4312846625","https://openalex.org/W4386076004","https://openalex.org/W4386185600","https://openalex.org/W4388778348"],"related_works":["https://openalex.org/W2912872656","https://openalex.org/W4246210236","https://openalex.org/W1571999748","https://openalex.org/W1982241259","https://openalex.org/W2169063751","https://openalex.org/W2098049229","https://openalex.org/W3023196456","https://openalex.org/W2123189663","https://openalex.org/W2100016924","https://openalex.org/W1891287906"],"abstract_inverted_index":{"Despite":[0],"the":[1,52,60,72,76,83,94,111,116,124,132,139,160,196,203,219],"remarkable":[2],"ability":[3],"of":[4,63,75,120,146,155,162],"Large":[5,28],"Vision-Language":[6],"Models":[7,30],"(LVLMs)":[8],"in":[9,27,55,167],"image":[10],"comprehension,":[11],"these":[12],"models":[13,176],"frequently":[14],"generate":[15],"plausible":[16],"yet":[17],"factually":[18],"incorrect":[19],"responses,":[20],"a":[21,45,91],"phenomenon":[22],"known":[23],"as":[24,44],"hallucination.":[25],"Recently,":[26],"Language":[29],"(LLMs),":[31],"augmenting":[32,69],"LLMs":[33],"by":[34,82,104,189],"retrieving":[35],"information":[36],"from":[37],"external":[38],"knowledge":[39],"resources":[40],"has":[41],"been":[42],"proven":[43],"promising":[46],"solution":[47],"to":[48,68,101,142,217,222],"mitigate":[49,202],"hallucinations.":[50],"However,":[51],"retrieval":[53,112,127,134,140,152,192,197,220,230,233],"augmentation":[54,221],"LVLM":[56,175],"significantly":[57],"lags":[58],"behind":[59],"widespread":[61],"applications":[62],"LVLM.":[64],"Moreover,":[65],"when":[66],"transferred":[67],"LVLMs,":[70],"sometimes":[71],"hallucination":[73,204],"degree":[74],"model":[77,166],"is":[78],"even":[79],"exacerbated.":[80],"Motivated":[81],"research":[84],"gap":[85],"and":[86,129,136,179,194,231],"counter-intuitive":[87],"phenomenon,":[88],"we":[89,170,199],"introduce":[90],"novel":[92],"framework,":[93],"Active":[95],"Retrieval-Augmented":[96],"(ARA)":[97],"LVLM,":[98],"specifically":[99],"designed":[100],"address":[102],"hallucinations":[103,226],"incorporating":[105],"three":[106,172],"critical":[107],"dimensions:":[108],"(i)":[109],"dissecting":[110],"targets":[113],"based":[114],"on":[115],"inherent":[117],"hierarchical":[118],"structures":[119],"images;":[121],"(ii)":[122],"pinpointing":[123],"most":[125],"effective":[126,229],"methods":[128],"filtering":[130],"out":[131],"reliable":[133],"results;":[135],"(iii)":[137],"timing":[138,195],"process":[141],"coincide":[143],"with":[144,227],"episodes":[145],"low":[147],"certainty,":[148],"while":[149],"circumventing":[150],"unnecessary":[151],"during":[153],"periods":[154],"high":[156],"certainty.":[157],"To":[158],"assess":[159],"capability":[161],"our":[163],"proposed":[164],"ARA":[165],"reducing":[168,225],"hallucination,":[169],"employ":[171],"widely":[173],"used":[174],"(LLaVA-1.5,":[177],"Qwen-VL,":[178],"mPLUG-Owl2)":[180],"across":[181],"four":[182],"benchmarks.":[183],"Our":[184],"empirical":[185],"observations":[186],"suggest":[187],"that":[188,208],"utilizing":[190],"fitting":[191],"mechanisms":[193],"judiciously,":[198],"can":[200,211],"effectively":[201],"problem.":[205],"We":[206],"hope":[207],"this":[209],"study":[210],"provide":[212],"deeper":[213],"insights":[214],"into":[215],"how":[216],"adapt":[218],"LVLMs":[223],"for":[224],"more":[228],"minimal":[232],"occurrences.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
