{"id":"https://openalex.org/W7147025577","doi":"https://doi.org/10.1145/3797025","title":"Mitigating Multilingual Hallucination in Large Vision-Language Models","display_name":"Mitigating Multilingual Hallucination in Large Vision-Language Models","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147025577","doi":"https://doi.org/10.1145/3797025"},"language":"en","primary_location":{"id":"doi:10.1145/3797025","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797025","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3797025","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":false,"raw_author_name":"Xiaoye Qu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4907-3978","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132648390","display_name":"Mingyang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Song","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-5181-1326","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"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"],"raw_orcid":"https://orcid.org/0000-0003-4488-0102","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132547129","display_name":"Daizong Liu","orcid":null},"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"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daizong Liu","raw_affiliation_strings":["Peking University, Beijing, China and Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8179-4508","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China and Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132610266","display_name":"Jianfeng Dong","orcid":null},"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"],"raw_orcid":"https://orcid.org/0000-0001-5244-3274","affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University, Hangzhou, China","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112778670","display_name":"Ya\u2010Min Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Cheng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7901-8662","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.5419,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98776611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4453999996185303,"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":0.4453999996185303,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07289999723434448,"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/T14347","display_name":"Big Data and Digital Economy","score":0.04800000041723251,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/leverage","display_name":"Leverage (statistics)","score":0.746999979019165},{"id":"https://openalex.org/keywords/multilingualism","display_name":"Multilingualism","score":0.43849998712539673},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3668000102043152},{"id":"https://openalex.org/keywords/auditory-hallucination","display_name":"Auditory hallucination","score":0.31119999289512634},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.29660001397132874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418999910354614},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.746999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023999810218811},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40880000591278076},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C2776706361","wikidata":"https://www.wikidata.org/wiki/Q1054088","display_name":"Auditory hallucination","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797025","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797025","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3797025","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797025","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1095643889","display_name":null,"funder_award_id":"62276110 and 62172039","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2963518342","https://openalex.org/W4312846625","https://openalex.org/W4364302332","https://openalex.org/W4391287688","https://openalex.org/W4392172801","https://openalex.org/W4402703048","https://openalex.org/W4402753774","https://openalex.org/W4411177432"],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Vision-Language":[2],"Models":[3],"(LVLMs)":[4],"have":[5],"exhibited":[6],"remarkable":[7],"capabilities":[8,97,190],"across":[9],"a":[10,87,107,156,196,243],"wide":[11],"range":[12],"of":[13,175,182,191],"tasks,":[14],"they":[15],"suffer":[16],"from":[17,93],"hallucination":[18,33,72,83,121,247],"problems,":[19],"where":[20],"models":[21],"generate":[22],"plausible":[23],"yet":[24],"incorrect":[25],"answers":[26,145],"given":[27,146],"the":[28,41,56,64,130,147,167,178,188,192,212,230],"input":[29,148,208],"image-query":[30,207],"pair.":[31],"This":[32],"phenomenon":[34],"is":[35,86,163],"even":[36],"more":[37],"severe":[38],"when":[39],"querying":[40],"image":[42],"in":[43,52,73,84,95,129,246],"non-English":[44,136],"languages,":[45],"while":[46],"existing":[47],"methods":[48],"for":[49,114,122,205,215,224,249],"mitigating":[50],"hallucinations":[51],"LVLMs":[53,85,231],"only":[54],"consider":[55],"English":[57],"scenarios.":[58],"In":[59],"this":[60,69,103],"article,":[61],"we":[62,79,105,150,185],"make":[63],"first":[65,131],"attempt":[66],"to":[67,117,120,170,228,232],"mitigate":[68],"important":[70],"multilingual":[71,82,96,152,157,172,183],"LVLMs.":[74,250],"With":[75],"thorough":[76],"experimental":[77],"analysis,":[78],"found":[80],"that":[81,90,134,239],"systemic":[88],"problem":[89],"could":[91],"arise":[92],"deficiencies":[94],"or":[98],"inadequate":[99],"multimodal":[100],"abilities.":[101],"To":[102],"end,":[104],"propose":[106,195],"two-stage":[108],"Multilingual":[109],"Hallucination":[110],"Removal":[111],"(MHR)":[112],"framework":[113],"LVLMs,":[115],"aiming":[116],"improve":[118],"resistance":[119],"both":[123],"high-resource":[124],"and":[125,142,194,209,253],"low-resource":[126],"languages.":[127],"Specifically,":[128],"stage,":[132],"considering":[133],"most":[135],"languages":[137],"cannot":[138],"follow":[139],"instructions":[140],"well":[141],"output":[143],"non-sense":[144],"image,":[149],"boost":[151],"instruction-following":[153],"ability":[154,169],"with":[155],"supervised":[158],"fine-tuning.":[159],"The":[160],"second":[161],"phase":[162],"aimed":[164],"at":[165,258],"enhancing":[166],"LVLM\u2019s":[168],"diminish":[171],"hallucinations.":[173],"Instead":[174],"relying":[176],"on":[177],"intricate":[179],"manual":[180],"annotations":[181],"resources,":[184],"fully":[186],"leverage":[187],"inherent":[189],"LVLM":[193],"novel":[197],"cross-lingual":[198],"alignment":[199],"method,":[200],"which":[201],"generates":[202],"multiple":[203],"responses":[204],"each":[206,216],"then":[210],"identifies":[211],"hallucination-aware":[213],"pairs":[214,220],"language.":[217],"These":[218],"data":[219],"are":[221,256],"finally":[222],"used":[223],"direct":[225],"preference":[226],"optimization":[227],"prompt":[229],"favor":[233],"non-hallucinating":[234],"responses.":[235],"Experimental":[236],"results":[237],"show":[238],"our":[240],"MHR":[241],"achieves":[242],"substantial":[244],"reduction":[245],"generation":[248],"Our":[251],"code":[252],"model":[254],"weights":[255],"available":[257],"https://github.com/ssmisya/MHR":[259],".":[260]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-02T00:00:00"}
