{"id":"https://openalex.org/W7127381337","doi":"https://doi.org/10.1109/tpami.2026.3656175","title":"Evaluating and Mitigating Relationship Hallucinations in Large Vision-Language Models","display_name":"Evaluating and Mitigating Relationship Hallucinations in Large Vision-Language Models","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127381337","doi":"https://doi.org/10.1109/tpami.2026.3656175","pmid":"https://pubmed.ncbi.nlm.nih.gov/41632655"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3656175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3656175","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5124939298","display_name":"Mingrui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Wu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0009-8633-758X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038372004","display_name":"Jiale Li","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Li","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0001-3717-1255","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101976912","display_name":"Jiayi Ji","orcid":"https://orcid.org/0000-0002-8641-6183"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-9956-6308","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012604813","display_name":"Fei Hao","orcid":"https://orcid.org/0000-0002-2295-7255"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fei Hao","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124932372","display_name":"Xiaoshuai Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124909478","display_name":"Rongrong Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12030939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"6","first_page":"6332","last_page":"6346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5799999833106995,"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":0.5799999833106995,"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":0.07320000231266022,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.03400000184774399,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.8549000024795532},{"id":"https://openalex.org/keywords/neglect","display_name":"Neglect","score":0.5903000235557556},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5855000019073486},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4729999899864197},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43209999799728394}],"concepts":[{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.8549000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007000207901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942000150680542},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5595999956130981},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42089998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3656175","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3656175","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41632655","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41632655","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4394899636","display_name":null,"funder_award_id":"2023M732948","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7857155408","display_name":null,"funder_award_id":"62302411","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8030850267","display_name":null,"funder_award_id":"2022ZD0118201","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2277195237","https://openalex.org/W2307512708","https://openalex.org/W2904565150","https://openalex.org/W2962735233","https://openalex.org/W2962858109","https://openalex.org/W3167939936","https://openalex.org/W4285255856","https://openalex.org/W4285294723","https://openalex.org/W4288083516","https://openalex.org/W4312344082","https://openalex.org/W4382240040","https://openalex.org/W4384873226","https://openalex.org/W4385572347","https://openalex.org/W4389523832","https://openalex.org/W4390874575","https://openalex.org/W4391287688","https://openalex.org/W4393159464","https://openalex.org/W4393160204","https://openalex.org/W4402683883","https://openalex.org/W4402703048","https://openalex.org/W4402704633","https://openalex.org/W4402716381","https://openalex.org/W4402716477","https://openalex.org/W4402726948","https://openalex.org/W4402727405","https://openalex.org/W4402727490","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402727851","https://openalex.org/W4402753774","https://openalex.org/W4403081466","https://openalex.org/W4404199641","https://openalex.org/W4405595839","https://openalex.org/W4405596328","https://openalex.org/W4405908117","https://openalex.org/W4410536678","https://openalex.org/W4410706693","https://openalex.org/W4411726009","https://openalex.org/W4412888636","https://openalex.org/W4413145646","https://openalex.org/W4413147327","https://openalex.org/W4414199061","https://openalex.org/W4415709366","https://openalex.org/W7133193597","https://openalex.org/W7133220561","https://openalex.org/W7160196396"],"related_works":[],"abstract_inverted_index":{"The":[0],"issue":[1],"of":[2,70,92],"hallucinations":[3,36,57,87,134],"is":[4],"a":[5,50,137],"prevalent":[6],"concern":[7],"in":[8,37,58,103,120],"existing":[9],"Large":[10],"Vision-Language":[11],"Models":[12],"(LVLMs).":[13],"Previous":[14],"efforts":[15,34],"have":[16],"primarily":[17],"focused":[18],"on":[19,113],"investigating":[20],"object":[21,30],"hallucinations,":[22],"which":[23],"can":[24],"be":[25],"easily":[26],"alleviated":[27],"by":[28,99],"introducing":[29],"detectors.":[31],"However,":[32],"these":[33],"neglect":[35],"inter-object":[38],"relationships,":[39],"essential":[40],"for":[41],"visual":[42,59,80,104,110],"comprehension.":[43,81],"In":[44],"this":[45],"work,":[46],"we":[47],"introduce":[48],"R-Bench,":[49],"novel":[51],"benchmark":[52],"specifically":[53],"designed":[54],"to":[55,66,148],"evaluate":[56],"relationships.":[60],"R-Bench":[61],"includes":[62],"both":[63],"image-level":[64],"questions":[65,74],"assess":[67],"the":[68,100],"existence":[69],"relationships":[71],"and":[72,96,135,156],"instance-level":[73],"that":[75,85,127,144],"probe":[76],"deeper":[77],"into":[78],"local":[79],"Our":[82],"analysis":[83],"reveals":[84],"relationship":[86,133],"arise":[88],"from":[89,116],"three":[90],"types":[91],"co-occurrences:":[93],"relationship-relationship,":[94],"subject-relationship,":[95],"relationship-object,":[97],"exacerbated":[98],"long-tail":[101],"distribution":[102],"datasets.":[105],"Moreover,":[106],"LVLMs":[107],"often":[108],"ignore":[109],"content,":[111],"over-relying":[112],"common":[114],"sense":[115],"language":[117],"models,":[118],"particularly":[119],"spatial":[121],"reasoning":[122],"tasks.":[123],"We":[124],"further":[125],"demonstrate":[126],"region-level":[128],"image-text":[129],"alignment":[130,152],"helps":[131],"mitigate":[132],"propose":[136],"new":[138],"baseline,":[139],"Region-Aware":[140],"Alignment":[141],"Mitigation":[142],"(RA$^{2}$2M),":[143],"enhances":[145],"model":[146],"attention":[147],"relevant":[149],"regions,":[150],"improving":[151],"between":[153],"generated":[154],"text":[155],"images.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-04T00:00:00"}