{"id":"https://openalex.org/W4412888636","doi":"https://doi.org/10.18653/v1/2025.findings-acl.322","title":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","display_name":"Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888636","doi":"https://doi.org/10.18653/v1/2025.findings-acl.322"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.322","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.322","pdf_url":"https://aclanthology.org/2025.findings-acl.322.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.322.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106421126","display_name":"Kening Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kening Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620625","display_name":"Junkai Chen","orcid":"https://orcid.org/0009-0000-9945-7729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junkai Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yibo Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibo Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029723914","display_name":"Xin Zou","orcid":"https://orcid.org/0000-0001-5031-5076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066119228","display_name":"Huiyu Zhou","orcid":"https://orcid.org/0000-0003-1634-9840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiyu Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109782052","display_name":"Xuming Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuming Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0351,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96666442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6193","last_page":"6212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8138999938964844,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8138999938964844,"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/T12488","display_name":"Mental Health via Writing","score":0.8019999861717224,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7501999735832214,"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/relation","display_name":"Relation (database)","score":0.7614880800247192},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.753345787525177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7012627124786377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45007872581481934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4444335997104645},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17359542846679688},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07963195443153381},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07217714190483093}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7614880800247192},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.753345787525177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012627124786377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45007872581481934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4444335997104645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17359542846679688},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07963195443153381},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07217714190483093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.322","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.322","pdf_url":"https://aclanthology.org/2025.findings-acl.322.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.322","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.322","pdf_url":"https://aclanthology.org/2025.findings-acl.322.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/13","score":0.6299999952316284,"display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888636.pdf","grobid_xml":"https://content.openalex.org/works/W4412888636.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Hallucination":[0],"issues":[1],"continue":[2],"to":[3,47,101],"affect":[4],"multimodal":[5,134],"large":[6],"language":[7],"models":[8],"(MLLMs),":[9],"with":[10],"existing":[11],"research":[12],"mainly":[13],"addressing":[14],"objectlevel":[15],"or":[16],"attribute-level":[17],"hallucinations,":[18,62,74],"neglecting":[19],"the":[20,86,114],"more":[21],"complex":[22],"relation":[23,31,61,73,103],"hallucinations":[24,32],"that":[25],"require":[26],"advanced":[27],"reasoning.Current":[28],"benchmarks":[29],"for":[30,131],"lack":[33],"detailed":[34],"evaluation":[35,93],"and":[36,39,77,80],"effective":[37],"mitigation,":[38],"their":[40],"datasets":[41],"often":[42],"suffer":[43],"from":[44],"biases":[45],"due":[46],"systematic":[48,70],"annotation":[49],"processes.To":[50],"address":[51],"these":[52],"challenges,":[53],"we":[54,105],"introduce":[55],"Reefknot,":[56],"a":[57,69,82,107],"comprehensive":[58],"benchmark":[59],"targeting":[60],"comprising":[63],"over":[64],"20,000":[65],"realworld":[66],"samples.We":[67],"provide":[68],"definition":[71],"of":[72,120],"integrating":[75],"perceptive":[76],"cognitive":[78],"perspectives,":[79],"construct":[81],"relation-based":[83],"corpus":[84],"using":[85],"Visual":[87],"Genome":[88],"scene":[89],"graph":[90],"dataset.Our":[91],"comparative":[92],"reveals":[94],"significant":[95],"limitations":[96],"in":[97],"current":[98],"MLLMs'":[99],"ability":[100],"handle":[102],"hallucinations.Additionally,":[104],"propose":[106],"novel":[108],"confidence-based":[109],"mitigation":[110],"strategy,":[111],"which":[112],"reduces":[113],"hallucination":[115],"rate":[116],"by":[117],"an":[118],"average":[119],"9.75%":[121],"across":[122],"three":[123],"datasets,":[124],"including":[125],"Reefknot.Our":[126],"work":[127],"offers":[128],"valuable":[129],"insights":[130],"achieving":[132],"trustworthy":[133],"intelligence.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}