{"id":"https://openalex.org/W4417073202","doi":"https://doi.org/10.1145/3743093.3770933","title":"Mitigating Hallucinations in Large Vision-Language Models via Dual Contrastive Decoding","display_name":"Mitigating Hallucinations in Large Vision-Language Models via Dual Contrastive Decoding","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073202","doi":"https://doi.org/10.1145/3743093.3770933"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3770933","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770933","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770933","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770933","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055698483","display_name":"Jiulong Wu","orcid":"https://orcid.org/0009-0007-1635-3440"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiulong Wu","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-1635-3440","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yucheng Shen","orcid":"https://orcid.org/0009-0006-6718-4942"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Shen","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-6718-4942","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haixin Sun","orcid":"https://orcid.org/0009-0006-4773-4521"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixin Sun","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-4773-4521","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111346891","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-6628-0370"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":["Soochow University, suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6628-0370","affiliations":[{"raw_affiliation_string":"Soochow University, suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.36970001459121704,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.36970001459121704,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0706000030040741,"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":0.06830000132322311,"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/decoding-methods","display_name":"Decoding methods","score":0.6855000257492065},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6678000092506409},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6460000276565552},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5449000000953674},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.535099983215332},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.439300000667572},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4316999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433000206947327},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6855000257492065},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6678000092506409},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6460000276565552},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534500002861023},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3743093.3770933","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770933","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770933","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3743093.3770933","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3743093.3770933","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3743093.3770933","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6781587187","display_name":null,"funder_award_id":"62476188","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"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417073202.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2963518342","https://openalex.org/W3034287395","https://openalex.org/W4308713560","https://openalex.org/W4312846625","https://openalex.org/W4386071687","https://openalex.org/W4386848004","https://openalex.org/W4402670231","https://openalex.org/W4402704633","https://openalex.org/W4402727405","https://openalex.org/W4402727764","https://openalex.org/W4402753774","https://openalex.org/W4404356490","https://openalex.org/W4405596328"],"related_works":[],"abstract_inverted_index":{"Large":[0,30],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"shown":[5],"impressive":[6],"performance":[7,142],"across":[8],"diverse":[9],"multimodal":[10],"tasks.":[11,149],"However,":[12],"their":[13,52],"trustworthiness":[14],"is":[15],"challenged":[16],"by":[17,72,81],"two":[18],"types":[19],"of":[20,27,104,112],"hallucinations:":[21],"over-reliance":[22],"on":[23,86,119,143],"the":[24,28,101,109,132],"language":[25,70],"priors":[26,71],"underlying":[29],"Language":[31],"Model":[32],"(LLM)":[33],"and":[34,38,54,76,96,134,147,152],"misalignment":[35],"between":[36],"visual":[37],"textual":[39],"modalities.":[40],"Most":[41],"existing":[42],"hallucination":[43],"mitigation":[44],"methods":[45],"often":[46],"require":[47],"high":[48],"training":[49,95],"costs,":[50],"limiting":[51],"effectiveness":[53],"robustness.":[55],"To":[56],"address":[57],"this,":[58],"we":[59],"propose":[60],"Dual":[61],"Contrastive":[62],"Decoding":[63],"(DCD),":[64],"which":[65],"mitigates":[66,128],"hallucinations":[67,129],"stemming":[68],"from":[69],"subtracting":[73],"image-irrelevant":[74],"distributions":[75],"further":[77],"aligns":[78],"image-text":[79],"modalities":[80],"enabling":[82],"LVLMs":[83,113],"to":[84],"focus":[85],"correct":[87],"image":[88],"entities.":[89],"This":[90],"strategy":[91],"requires":[92],"no":[93],"additional":[94],"can":[97],"be":[98,155],"applied":[99],"during":[100],"decoding":[102],"phase":[103],"any":[105],"LVLM,":[106],"effectively":[107],"improving":[108],"inference":[110],"capability":[111],"at":[114,130],"minimal":[115],"cost.":[116],"Extensive":[117],"experiments":[118],"discriminative":[120],"(POPE,":[121],"MME)":[122],"benchmarks":[123],"demonstrate":[124],"that":[125],"DCD":[126],"significantly":[127],"both":[131],"object":[133],"attribute":[135],"levels,":[136],"while":[137],"also":[138],"enhancing":[139],"overall":[140],"model":[141],"general":[144],"vision-language":[145],"perception":[146],"recognition":[148],"The":[150],"code":[151],"dataset":[153],"will":[154],"made":[156],"available.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-06T00:00:00"}