{"id":"https://openalex.org/W4415540126","doi":"https://doi.org/10.1145/3746027.3755606","title":"Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models","display_name":"Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540126","doi":"https://doi.org/10.1145/3746027.3755606"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755606","pdf_url":null,"source":null,"license":null,"license_id":null,"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":["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/A5094006184","display_name":"Nanxing Hu","orcid":"https://orcid.org/0009-0009-5098-8137"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanxing Hu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5098-8137","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008233534","display_name":"Xiaoyue Duan","orcid":"https://orcid.org/0000-0002-2384-3559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyue Duan","raw_affiliation_strings":["Researcher, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2384-3559","affiliations":[{"raw_affiliation_string":"Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinchao Zhang","orcid":"https://orcid.org/0000-0003-4611-9675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchao Zhang","raw_affiliation_strings":["Researcher, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4611-9675","affiliations":[{"raw_affiliation_string":"Researcher, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011488839","display_name":"Guoliang Kang","orcid":"https://orcid.org/0000-0003-1978-2025"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Kang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1978-2025","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4778","last_page":"4787"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.926800012588501,"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/visual-hallucination","display_name":"Visual Hallucination","score":0.649399995803833},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5821999907493591},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.542900025844574},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5256999731063843},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.49559998512268066},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42080000042915344},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757000088691711},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5659000277519226},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.542900025844574},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.49559998512268066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.36820000410079956},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8115063663","display_name":null,"funder_award_id":"92370114","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2896348597","https://openalex.org/W2963518342","https://openalex.org/W4312846625","https://openalex.org/W4384662964","https://openalex.org/W4389520259","https://openalex.org/W4394862623","https://openalex.org/W4401362547","https://openalex.org/W4402727764","https://openalex.org/W4402727851","https://openalex.org/W4405596328"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"usually":[4],"generate":[5],"texts":[6],"which":[7,68,190],"satisfy":[8],"context":[9],"coherence":[10],"but":[11],"don't":[12],"match":[13],"the":[14,25,38,44,53,75,84,89,161,175,229],"visual":[15,45,60,76,90,117,132,182,197],"input.":[16],"Such":[17],"a":[18,56,98,154,164,187],"hallucination":[19,32,105,230],"issue":[20,231],"hinders":[21],"LVLMs'":[22],"applicability":[23],"in":[24,33,66,92,106,121],"real":[26],"world.":[27],"The":[28],"key":[29],"to":[30,36,51,63,103,127,134,159,186,204,209],"solving":[31],"LVLM":[34,96,107,139,233],"is":[35],"make":[37],"text":[39,93,207],"generation":[40,94,208],"rely":[41],"more":[42],"on":[43,181,194,214],"content.":[46],"Most":[47],"previous":[48,238],"works":[49],"choose":[50],"enhance/adjust":[52],"features/output":[54],"of":[55,95,177,232],"specific":[57],"modality":[58],"(i.e.,":[59],"or":[61,72],"textual)":[62],"alleviate":[64],"hallucinations":[65],"LVLM,":[67],"do":[69],"not":[70,115,192],"explicitly":[71],"systematically":[73],"enhance":[74],"reliance.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81,112,168,202],"comprehensively":[82],"investigate":[83],"factors":[85],"that":[86,114,170,223],"may":[87,140,184],"degenerate":[88],"reliance":[91],"from":[97,108,163,172],"Bayesian":[99,165],"perspective.":[100,166],"We":[101,125,152],"propose":[102,126,153,203],"mitigate":[104,228],"three":[109,215],"aspects.":[110],"Firstly,":[111],"observe":[113,169],"all":[116],"tokens":[118,133,183,198],"are":[119,241],"informative":[120,196],"generating":[122,149],"meaningful":[123],"texts.":[124],"evaluate":[128],"and":[129,220,234],"remove":[130],"redundant":[131],"avoid":[135,210],"their":[136],"disturbance.":[137],"Secondly,":[138],"encode":[141],"inappropriate":[142],"prior":[143,162,188],"information,":[144],"making":[145],"it":[146],"lean":[147],"toward":[148],"unexpected":[150],"words.":[151],"simple,":[155],"yet":[156],"effective":[157],"way":[158],"rectify":[160],"Thirdly,":[167],"starting":[171],"certain":[173],"steps,":[174],"posterior":[176],"next-token":[178],"prediction":[179],"conditioned":[180],"collapse":[185],"distribution":[189],"does":[191],"depend":[193],"any":[195],"at":[199,243],"all.":[200],"Thus,":[201],"stop":[205],"further":[206],"hallucination.":[211],"Extensive":[212],"experiments":[213],"benchmarks,":[216],"including":[217],"POPE,":[218],"CHAIR,":[219],"MME,":[221],"demonstrate":[222],"our":[224],"method":[225],"can":[226],"consistently":[227],"performs":[235],"favorably":[236],"against":[237],"state-of-the-arts.":[239],"Codes":[240],"available":[242],"https://github.com/NeilHnxTcc/EVRB.":[244]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}