{"id":"https://openalex.org/W4412888482","doi":"https://doi.org/10.18653/v1/2025.findings-acl.478","title":"MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors","display_name":"MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888482","doi":"https://doi.org/10.18653/v1/2025.findings-acl.478"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.478","pdf_url":"https://aclanthology.org/2025.findings-acl.478.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.478.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yishuo Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishuo Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048695439","display_name":"Renjie Gu","orcid":"https://orcid.org/0000-0003-2895-444X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjie Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018801428","display_name":"Jiaxu Li","orcid":"https://orcid.org/0000-0002-3740-1866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874857","display_name":"Xuancheng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuancheng Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003930227","display_name":"Junzhe Chen","orcid":"https://orcid.org/0009-0005-7573-0707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junzhe Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102325476","display_name":"Xiaotao Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaotao Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044042138","display_name":"Minlie Huang","orcid":"https://orcid.org/0000-0001-7111-1849"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minlie Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20116728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9197","last_page":"9222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11993","display_name":"Atomic and Subatomic Physics Research","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5909744501113892},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5903507471084595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36855262517929077},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07670339941978455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909744501113892},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5903507471084595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36855262517929077},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07670339941978455}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.478","pdf_url":"https://aclanthology.org/2025.findings-acl.478.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.478","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.478","pdf_url":"https://aclanthology.org/2025.findings-acl.478.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":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888482.pdf","grobid_xml":"https://content.openalex.org/works/W4412888482.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/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2366906938"],"abstract_inverted_index":{"Hallucination":[0],"remains":[1],"a":[2,53,115],"critical":[3],"challenge":[4],"for":[5,23,38,64,136],"multimodal":[6,80],"large":[7],"language":[8],"models":[9],"(MLLMs),":[10],"undermining":[11],"their":[12],"reliability":[13],"in":[14,68,142],"real-world":[15],"applications.While":[16],"fine-grained":[17],"hallucination":[18,76,140],"detection":[19],"(FHD)":[20],"holds":[21],"promise":[22],"enhancing":[24],"high-quality":[25],"vision-language":[26],"data":[27],"construction":[28],"and":[29,82,145],"model":[30,99,117],"alignment":[31],"through":[32],"enriched":[33],"feedback":[34],"signals,":[35],"automated":[36],"solutions":[37],"this":[39,110],"task":[40],"have":[41],"yet":[42],"to":[43],"be":[44,148],"systematically":[45],"explored.Inspired":[46],"by":[47],"the":[48,58,97,130],"concept":[49],"of":[50,87,106],"\"MLLM":[51],"as":[52],"Judge\",":[54],"we":[55,91,112],"introduce":[56],"MHALO,":[57],"first":[59],"comprehensive":[60],"benchmark":[61,72,131],"specifically":[62],"designed":[63],"evaluating":[65],"MLLMs'":[66],"capability":[67],"performing":[69],"token-level":[70],"FHD.Our":[71],"encompasses":[73],"12":[74],"distinct":[75],"types":[77],"spanning":[78],"both":[79],"perception":[81],"reasoning":[83],"domains.Through":[84],"extensive":[85],"evaluations":[86],"9":[88],"selected":[89],"MLLMs,":[90],"reveal":[92],"substantial":[93],"performance":[94],"limitations,":[95],"with":[96],"leading":[98],"achieving":[100],"an":[101],"average":[102],"F":[103],"1":[104],"IoU":[105],"only":[107],"40.59%.To":[108],"address":[109],"limitation,":[111],"develop":[113],"HALODET-4B,":[114],"specialized":[116],"trained":[118],"on":[119,139],"our":[120],"curated":[121],"training":[122],"data,":[123],"which":[124],"significantly":[125],"outperforms":[126],"existing":[127],"models.We":[128],"hope":[129],"can":[132],"provide":[133],"valuable":[134],"insights":[135],"future":[137],"research":[138],"mitigation":[141],"MLLMs.The":[143],"code":[144],"dataset":[146],"will":[147],"publicly":[149],"available":[150],"at":[151],"https:":[152],"//github.com/walkeralan123/MHALO.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}