{"id":"https://openalex.org/W4412888054","doi":"https://doi.org/10.18653/v1/2025.findings-acl.850","title":"Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization","display_name":"Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888054","doi":"https://doi.org/10.18653/v1/2025.findings-acl.850"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.850","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.850","pdf_url":"https://aclanthology.org/2025.findings-acl.850.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.850.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023050036","display_name":"Yuhan Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhan Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577090","display_name":"Ruobing Xie","orcid":"https://orcid.org/0000-0003-3170-5647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruobing Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039337290","display_name":"Xingwu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingwu Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020128898","display_name":"Zhanhui Kang","orcid":"https://orcid.org/0009-0006-5151-4222"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanhui Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101810699","display_name":"Xirong Li","orcid":"https://orcid.org/0000-0003-0787-8230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xirong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8949119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16563","last_page":"16577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.8942000269889832,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.8942000269889832,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.8737000226974487,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.858299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5832615494728088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5568816065788269},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.4769379496574402},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4215892553329468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40643811225891113},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3052722215652466},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11951082944869995},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08033561706542969}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5832615494728088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5568816065788269},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.4769379496574402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4215892553329468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40643811225891113},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3052722215652466},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11951082944869995},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08033561706542969},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.850","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.850","pdf_url":"https://aclanthology.org/2025.findings-acl.850.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.850","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.850","pdf_url":"https://aclanthology.org/2025.findings-acl.850.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5199999809265137,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3114819178","display_name":null,"funder_award_id":"2023QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6518577882","display_name":null,"funder_award_id":"62172420","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888054.pdf","grobid_xml":"https://content.openalex.org/works/W4412888054.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2419430421","https://openalex.org/W2334811251","https://openalex.org/W2386464051","https://openalex.org/W32883749","https://openalex.org/W2308791691","https://openalex.org/W1972094787","https://openalex.org/W1971933602","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"are":[5],"known":[6],"to":[7,17,23,49],"hallucinate,":[8],"which":[9],"limits":[10],"their":[11,61],"practical":[12],"applications.Recent":[13],"works":[14],"have":[15,30],"attempted":[16],"apply":[18],"Direct":[19,45],"Preference":[20,46],"Optimization":[21,47],"(DPO)":[22],"enhance":[24],"the":[25,75,113,124,131],"performance":[26,100],"of":[27,70,78,115,126],"MLLMs,":[28],"but":[29],"shown":[31],"inconsistent":[32],"improvements":[33,135],"in":[34,52],"mitigating":[35],"hallucinations.To":[36],"address":[37],"this":[38],"issue":[39],"more":[40],"effectively,":[41],"we":[42,66],"introduce":[43],"Hallucination-targeted":[44],"(HDPO)":[48],"reduce":[50],"hallucinations":[51,59],"MLLMs.Unlike":[53],"previous":[54],"approaches,":[55],"our":[56,96,116,127],"method":[57,97,128],"tackles":[58],"from":[60],"diverse":[62],"forms":[63],"and":[64,89,111,119,129],"causes.Specifically,":[65],"develop":[67],"three":[68],"types":[69],"preference":[71],"pair":[72],"data":[73],"targeting":[74],"following":[76],"causes":[77],"MLLM":[79],"hallucinations:":[80],"(1)":[81],"insufficient":[82],"visual":[83],"capabilities,":[84],"(2)":[85],"long":[86],"context":[87],"generation,":[88],"(3)":[90],"multimodal":[91],"conflicts.Experimental":[92],"results":[93],"demonstrate":[94],"that":[95],"achieves":[98],"superior":[99],"across":[101],"multiple":[102],"hallucination":[103],"evaluation":[104],"datasets,":[105],"surpassing":[106],"most":[107],"state-of-the-art":[108],"(SOTA)":[109],"methods":[110],"highlighting":[112],"potential":[114,132],"approach.Ablation":[117],"studies":[118],"in-depth":[120],"analyses":[121],"further":[122,134],"confirm":[123],"effectiveness":[125],"suggest":[130],"for":[133],"through":[136],"scaling":[137],"up.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}