{"id":"https://openalex.org/W4415709366","doi":"https://doi.org/10.1109/icme59968.2025.11209377","title":"Beyond Multimodal Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","display_name":"Beyond Multimodal Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709366","doi":"https://doi.org/10.1109/icme59968.2025.11209377"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5100575091","display_name":"Zhiyuan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Zhao","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059575276","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-4748-6426"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104670548","display_name":"Linke Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linke Ouyang","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100303463","display_name":"Xiaoyi Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Dong","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365369","display_name":"Jiaqi Wang","orcid":"https://orcid.org/0000-0002-8523-3975"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101615091","display_name":"Conghui He","orcid":"https://orcid.org/0000-0001-8697-695X"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conghui He","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100575091"],"corresponding_institution_ids":["https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":5.5605,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96056522,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.11159999668598175,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.11159999668598175,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10667","display_name":"Emotion and Mood Recognition","score":0.09279999881982803,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08990000188350677,"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/preference","display_name":"Preference","score":0.7059000134468079},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6047000288963318},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3179999887943268},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2809999883174896}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7059000134468079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442000269889832},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6025999784469604},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3937999904155731},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2962735233","https://openalex.org/W4389523832","https://openalex.org/W4393160204","https://openalex.org/W4402670859","https://openalex.org/W4402727764","https://openalex.org/W4402727851","https://openalex.org/W4403081466"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3,27],"have":[4],"made":[5],"significant":[6,136],"advancements":[7],"in":[8,24],"recent":[9],"years,":[10],"yet":[11],"they":[12],"still":[13],"suffer":[14],"from":[15,38],"a":[16,44,58,97,125],"common":[17],"issue":[18],"known":[19],"as":[20,57],"the":[21,26,54,68,77,112],"\"hallucination":[22],"problem\",":[23],"which":[25,52,123],"generate":[28],"textual":[29],"descriptions":[30],"that":[31],"inaccurately":[32],"depict":[33],"or":[34],"entirely":[35],"fabricate":[36],"content":[37],"associated":[39],"images.":[40],"This":[41],"paper":[42,82],"introduces":[43],"novel":[45],"solution,":[46],"Hallucination-Aware":[47],"Direct":[48],"Preference":[49],"Optimization":[50],"(HA-DPO),":[51],"reframes":[53],"hallucination":[55,129],"problem":[56],"preference":[59],"selection":[60],"task.":[61],"The":[62],"model":[63,108],"is":[64],"trained":[65],"to":[66],"favor":[67],"non-hallucinatory":[69],"response":[70],"when":[71],"presented":[72],"with":[73,100,106],"two":[74],"responses":[75],"of":[76,103,114],"same":[78],"image.":[79],"Meanwhile,":[80],"this":[81],"proposes":[83],"an":[84],"automated":[85],"pipeline":[86],"for":[87],"constructing":[88],"positive":[89],"(non-hallucinatory)":[90],"and":[91,127,142,147],"negative":[92],"(hallucinatory)":[93],"sample":[94],"pairs,":[95],"ensuring":[96],"style-consistent":[98],"dataset":[99],"varied":[101],"types":[102],"hallucinations":[104],"aligns":[105],"real-world":[107],"outputs.":[109],"Lastly,":[110],"regarding":[111],"limitations":[113],"existing":[115],"benchmarks,":[116],"we":[117],"propose":[118],"Sentence-Level":[119],"Hallucination":[120],"Ratio":[121],"(SHR),":[122],"offers":[124],"broader":[126],"fine-grained":[128],"evaluation.":[130],"With":[131],"extensive":[132],"experiments,":[133],"HA-DPO":[134],"shows":[135],"hallucination-mitigating":[137],"performance":[138],"on":[139],"different":[140],"LVLMs":[141],"metrics,":[143],"proving":[144],"its":[145],"effectiveness":[146],"generality.":[148],"Code":[149],"available":[150],"at":[151],"https://github.com/opendatalab/HA-DPO#.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}