{"id":"https://openalex.org/W4416036551","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.982","title":"Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization","display_name":"Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036551","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.982"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.982","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.982","pdf_url":"https://aclanthology.org/2025.emnlp-main.982.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.982.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043129695","display_name":"Kesheng Wu","orcid":"https://orcid.org/0000-0002-6907-3393"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiulong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056055301","display_name":"Zhiao Shi","orcid":"https://orcid.org/0000-0002-1220-1219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengliang Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050255638","display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuaiqiang Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005312000","display_name":"Jizhou Huang","orcid":"https://orcid.org/0000-0003-1022-0309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jizhou Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050161084","display_name":"Lingyong Yan","orcid":"https://orcid.org/0000-0002-6547-1984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingyong Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055774883","display_name":"Min Cao","orcid":"https://orcid.org/0000-0003-3249-321X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060166716","display_name":"Min Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5043129695"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1715,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84378764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19456","last_page":"19472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1873999983072281,"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":0.1873999983072281,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.147599995136261,"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/T14347","display_name":"Big Data and Digital Economy","score":0.045099999755620956,"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/preference","display_name":"Preference","score":0.42260000109672546},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.2547000050544739},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.25099998712539673},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2296999990940094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.22869999706745148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5400999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611000120639801},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24529999494552612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2296999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22869999706745148},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2222999930381775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.982","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.982","pdf_url":"https://aclanthology.org/2025.emnlp-main.982.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.982","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.982","pdf_url":"https://aclanthology.org/2025.emnlp-main.982.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6781587187","display_name":null,"funder_award_id":"62476188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","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"},{"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/W4416036551.pdf","grobid_xml":"https://content.openalex.org/works/W4416036551.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0,34],"Visual":[1],"Language":[2,35],"Models":[3,36],"(LVLMs)":[4],"have":[5],"demonstrated":[6],"impressive":[7],"capabilities":[8],"across":[9,102],"multiple":[10],"tasks.However,":[11],"their":[12,32],"trustworthiness":[13],"is":[14],"often":[15],"challenged":[16],"by":[17,128],"hallucinations,":[18],"which":[19,71],"can":[20],"be":[21,140],"attributed":[22],"to":[23,82,96],"the":[24,28,84,120],"modality":[25,53,74],"misalignment":[26],"and":[27,60,107,114,132,137],"inherent":[29],"hallucinations":[30],"of":[31,86,122],"underlying":[33],"(LLMs)":[37],"backbone.Existing":[38],"preference":[39,79,89,100,112],"alignment":[40,75,80],"methods":[41],"focus":[42],"on":[43,58,109,130,134],"aligning":[44],"model":[45],"responses":[46],"with":[47],"human":[48,78,111],"preferences":[49],"while":[50],"neglecting":[51],"image-text":[52],"alignment,":[54],"resulting":[55],"in":[56],"over-reliance":[57],"LLMs":[59],"hallucinations.In":[61],"this":[62],"paper,":[63],"we":[64,91],"propose":[65],"Entity-centric":[66],"Multimodal":[67],"Preference":[68],"Optimization":[69],"(EMPO),":[70],"achieves":[72],"enhanced":[73],"than":[76],"existing":[77],"methods.Besides,":[81],"overcome":[83],"scarcity":[85],"high-quality":[87],"multimodal":[88,116],"data,":[90],"utilize":[92],"open-source":[93],"instruction":[94],"datasets":[95,113],"automatically":[97],"construct":[98],"highquality":[99],"data":[101],"three":[103],"aspects:":[104],"image,":[105],"instruction,":[106],"response.Experiments":[108],"two":[110],"five":[115],"hallucination":[117,126],"benchmarks":[118],"demonstrate":[119],"effectiveness":[121],"EMPO,":[123],"e.g.,":[124],"reducing":[125],"rates":[127],"85.9%":[129],"Object-HalBench":[131],"49.8%":[133],"MM-HalBench.The":[135],"code":[136],"dataset":[138],"will":[139],"released":[141],"at":[142],"https:":[143],"//github.com/RobitsG/EMPO.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-11-08T00:00:00"}