{"id":"https://openalex.org/W4414384496","doi":"https://doi.org/10.1109/iccv51701.2025.00244","title":"Inter: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling","display_name":"Inter: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414384496","doi":"https://doi.org/10.1109/iccv51701.2025.00244"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.05056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Dong","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017665185","display_name":"Shichao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Shichao Dong","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000843982","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0003-0194-7549"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452304","display_name":"L. P. Zhou","orcid":"https://orcid.org/0000-0002-7234-3542"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Li Zhou","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016122961","display_name":"Zenghui Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Zenghui Sun","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013812973","display_name":"Lihua Jing","orcid":"https://orcid.org/0009-0005-6369-7890"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Jing","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101243690","display_name":"J. Lan","orcid":"https://orcid.org/0009-0006-4423-2403"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Jinsong Lan","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101658239","display_name":"Xiaoyong Zhu","orcid":"https://orcid.org/0000-0002-5056-6171"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Xiaoyong Zhu","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101622992","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-2531-3383"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28855532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2534","last_page":"2544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10094","display_name":"Epilepsy research and treatment","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10094","display_name":"Epilepsy research and treatment","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7064999938011169},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6547999978065491},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6018000245094299},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4156999886035919},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.40149998664855957},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38769999146461487},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.38269999623298645}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6547999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517000198364258},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5647000074386597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4634000062942505},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37709999084472656},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2992048920","wikidata":"https://www.wikidata.org/wiki/Q7256367","display_name":"Psychological science","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26440000534057617}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.05056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05056","pdf_url":"https://arxiv.org/pdf/2507.05056","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.05056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.05056","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.05056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05056","pdf_url":"https://arxiv.org/pdf/2507.05056","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hallucinations":[0],"in":[1,32,50],"large":[2],"vision-language":[3],"models":[4],"(LVLMs)":[5],"pose":[6],"significant":[7],"challenges":[8],"for":[9,65],"real-world":[10],"applications,":[11],"as":[12],"LVLMs":[13,84,98,128,165],"may":[14],"generate":[15],"responses":[16],"that":[17,37,88,117],"appear":[18],"plausible":[19],"yet":[20],"remain":[21],"inconsistent":[22],"with":[23],"the":[24,61,168,178],"associated":[25],"visual":[26],"content.":[27],"This":[28],"issue":[29],"rarely":[30],"occurs":[31],"human":[33],"cognition.":[34],"We":[35],"argue":[36],"this":[38,76],"discrepancy":[39],"arises":[40],"from":[41],"humans'":[42],"ability":[43],"to":[44,129,161,167],"effectively":[45,130],"leverage":[46],"multimodal":[47,58,100,135],"interaction":[48,136],"information":[49,137],"data":[51],"samples.":[52,101],"Specifically,":[53,124],"humans":[54],"typically":[55],"first":[56],"gather":[57],"information,":[59],"analyze":[60],"interactions":[62],"across":[63],"modalities":[64],"understanding,":[66],"and":[67,85,150],"then":[68],"express":[69],"their":[70,132],"understanding":[71,133],"through":[72],"language.":[73],"Motivated":[74],"by":[75],"observation,":[77],"we":[78,106],"conduct":[79],"extensive":[80],"experiments":[81],"on":[82,99,103,163],"popular":[83],"obtained":[86],"insights":[87],"surprisingly":[89],"reveal":[90],"human-like,":[91],"though":[92],"less":[93],"pronounced,":[94],"cognitive":[95],"behavior":[96],"of":[97,134,159],"Building":[102],"these":[104],"findings,":[105],"further":[107],"propose":[108],"\\textbf{INTER}:":[109],"\\textbf{Inter}action":[110],"Guidance":[111],"Sampling,":[112],"a":[113],"novel":[114],"training-free":[115],"algorithm":[116],"mitigate":[118],"hallucinations":[119],"without":[120],"requiring":[121],"additional":[122],"data.":[123],"INTER":[125,154],"explicitly":[126],"guides":[127],"reapply":[131],"when":[138,177],"generating":[139],"responses,":[140],"thereby":[141],"reducing":[142],"potential":[143],"hallucinations.":[144],"On":[145],"six":[146],"benchmarks":[147],"including":[148],"VQA":[149],"image":[151],"captioning":[152],"tasks,":[153],"achieves":[155],"an":[156],"average":[157],"improvement":[158],"up":[160],"3.4\\%":[162],"five":[164],"compared":[166],"state-of-the-art":[169],"decoding":[170],"strategy.":[171],"The":[172],"code":[173],"will":[174],"be":[175],"released":[176],"paper":[179],"is":[180],"accepted.":[181]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
