{"id":"https://openalex.org/W7166883838","doi":"https://doi.org/10.18653/v1/2026.acl-long.1742","title":"DiVE: Decoupling Intra-layer Visual Evidence for Mitigating Hallucinations in Large Vision-Language Models","display_name":"DiVE: Decoupling Intra-layer Visual Evidence for Mitigating Hallucinations in Large Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166883838","doi":"https://doi.org/10.18653/v1/2026.acl-long.1742"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1742","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1742","pdf_url":"https://aclanthology.org/2026.acl-long.1742.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1742.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139747498","display_name":"Xinwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Xinwei Li","raw_affiliation_strings":["School of Computer Science and Engineering , Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139775451","display_name":"Li Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Li Lin","raw_affiliation_strings":["School of Computer Science and Engineering , Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139811950","display_name":"Hui Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui Jiao","raw_affiliation_strings":["Faculty of Science and Engineering , Department of Computer Science , University of Liverpool"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Engineering , Department of Computer Science , University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792939","display_name":"Li Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Li Yao","raw_affiliation_strings":["School of Computer Science and Engineering , Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771214","display_name":"Tien-Tsin Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tien-Tsin Wong","raw_affiliation_strings":["Department of Data Science & AI , Faculty of Information Technology , Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science & AI , Faculty of Information Technology , Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139809174","display_name":"Hanqian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Hanqian Wu","raw_affiliation_strings":["School of Cyber Science and Engineering , Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering , Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.86396181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37552","last_page":"37568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13397","display_name":"Hallucinations in medical conditions","score":0.5467000007629395,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T13397","display_name":"Hallucinations in medical conditions","score":0.5467000007629395,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12553","display_name":"Psychedelics and Drug Studies","score":0.10090000182390213,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.07029999792575836,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2939999997615814},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.26579999923706055},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.25870001316070557},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.2540000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5370000004768372},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4187000095844269},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3977000117301941},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.310699999332428},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1742","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1742","pdf_url":"https://aclanthology.org/2026.acl-long.1742.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1742","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1742","pdf_url":"https://aclanthology.org/2026.acl-long.1742.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":[{"id":"https://openalex.org/G4476335453","display_name":null,"funder_award_id":"62402105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7463114173","display_name":null,"funder_award_id":"BK20230815","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166883838.pdf","grobid_xml":"https://content.openalex.org/works/W7166883838.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"Large":[1],"Vision-Language":[2],"Models":[3],"(LVLMs)":[4],"have":[5],"achieved":[6],"significant":[7],"progress":[8],"yet":[9],"frequently":[10],"suffer":[11],"from":[12,17,46],"visual":[13,25,44,65,74],"hallucinations,":[14],"often":[15,29],"stemming":[16],"an":[18,119],"over-reliance":[19],"on":[20,31,111],"language":[21,36],"priors":[22],"rather":[23],"than":[24],"evidence.Existing":[26],"decoding-based":[27],"approaches":[28],"rely":[30],"input":[32],"perturbations":[33],"to":[34,71,79,89],"weaken":[35],"priors,":[37],"but":[38],"they":[39],"do":[40],"not":[41],"explicitly":[42],"decouple":[43],"evidence":[45,78],"mixed":[47],"vision-language":[48],"representations.To":[49],"address":[50],"these":[51],"limitations,":[52],"we":[53],"propose":[54],"DiVE":[55,85,104],"(Decoupling":[56],"intra-layer":[57,69],"Visual":[58],"Evidence).DiVE":[59],"dynamically":[60],"identifies":[61],"layers":[62],"enriched":[63],"with":[64],"information":[66],"and":[67,126],"performs":[68],"decoupling":[70],"extract":[72],"aggregated":[73],"evidence.By":[75],"suppressing":[76],"this":[77],"construct":[80],"a":[81,124],"language-priordominated":[82],"reference":[83],"distribution,":[84],"employs":[86],"contrastive":[87],"decoding":[88],"calibrate":[90],"the":[91,116],"output":[92],"logits,":[93],"thereby":[94],"mitigating":[95],"hallucinations.Extensive":[96],"experiments":[97],"across":[98],"diverse":[99],"LVLM":[100],"architectures":[101],"demonstrate":[102],"that":[103],"achieves":[105],"state-of-the-art":[106],"performance":[107],"among":[108],"decodingbased":[109],"methods":[110],"multiple":[112],"benchmarks.Crucially,":[113],"it":[114],"eliminates":[115],"latency":[117],"of":[118],"extra":[120],"forward":[121],"pass,":[122],"offering":[123],"lightweight":[125],"efficient":[127],"solution.":[128]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}