{"id":"https://openalex.org/W7140133131","doi":"https://doi.org/10.18653/v1/2026.eacl-long.210","title":"Attribution-Guided Multi-Object Hallucination and Bias Detection in Vision-Language Models","display_name":"Attribution-Guided Multi-Object Hallucination and Bias Detection in Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140133131","doi":"https://doi.org/10.18653/v1/2026.eacl-long.210"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.210","doi":"https://doi.org/10.18653/v1/2026.eacl-long.210","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.210","pdf_url":"https://aclanthology.org/2026.eacl-long.210.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.eacl-long.210.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062827531","display_name":"Sirat Samyoun","orcid":"https://orcid.org/0000-0001-7914-6384","observed_orcids":["https://orcid.org/0000-0001-7914-6384"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirat Samyoun","raw_affiliation_strings":["TikTok Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038751210","display_name":"Yingtai Xiao","orcid":"https://orcid.org/0000-0001-8964-6753","observed_orcids":["https://orcid.org/0000-0001-8964-6753"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingtai Xiao","raw_affiliation_strings":["TikTok Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130398910","display_name":"Jian Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Du","raw_affiliation_strings":["TikTok Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok Inc","institution_ids":[]}]}],"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":0.16536057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4529","last_page":"4548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883000254631042,"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":0.9883000254631042,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00989999994635582,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hallucination-detection","display_name":"hallucination detection","score":0.8930000066757202},{"id":"https://openalex.org/keywords/bias-detection","display_name":"bias detection","score":0.8379999995231628},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9359999895095825},{"id":"https://openalex.org/keywords/shapley-value","display_name":"Shapley value","score":0.8309999704360962},{"id":"https://openalex.org/keywords/kernelshap","display_name":"KernelSHAP","score":0.9800000190734863},{"id":"https://openalex.org/keywords/attribution","display_name":"attribution","score":0.5379999876022339},{"id":"https://openalex.org/keywords/linguistic-bias","display_name":"language bias","score":0.8399999737739563}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4422000050544739},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30059999227523804},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25529998540878296},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24250000715255737},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.24230000376701355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.210","doi":"https://doi.org/10.18653/v1/2026.eacl-long.210","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.210","pdf_url":"https://aclanthology.org/2026.eacl-long.210.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.210","doi":"https://doi.org/10.18653/v1/2026.eacl-long.210","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.210","pdf_url":"https://aclanthology.org/2026.eacl-long.210.pdf","source":{"id":"https://openalex.org/S4306418011","display_name":"Conference of the European Chapter of the Association for Computational Linguistics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140133131.pdf","grobid_xml":"https://content.openalex.org/works/W7140133131.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7151794380","https://openalex.org/W7166815624","https://openalex.org/W7202127904","https://openalex.org/W7134857045","https://openalex.org/W7160926782","https://openalex.org/W7222928059","https://openalex.org/W7223116579","https://openalex.org/W7162420207","https://openalex.org/W7171964443","https://openalex.org/W7204916145"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"excel":[2],"in":[3,19],"multi-modal":[4],"tasks":[5],"but":[6],"often":[7],"hallucinate":[8],"objects":[9,39],"or":[10,37,44],"exhibit":[11],"linguistic":[12],"bias":[13,103,109],"by":[14,87,91],"over-repeating":[15],"object":[16],"names,":[17],"especially":[18],"complex":[20],"multi-object":[21,26],"scenes.Existing":[22],"methods":[23],"struggle":[24],"with":[25],"grounding":[27],"because":[28],"language":[29],"priors":[30],"frequently":[31],"dominate":[32],"visual":[33],"evidence,":[34],"causing":[35],"hallucinated":[36,69],"biased":[38,71],"to":[40,67,100],"produce":[41],"attention":[42],"distributions":[43],"similarity":[45],"scores":[46],"nearly":[47],"indistinguishable":[48],"from":[49],"those":[50],"of":[51],"real":[52],"objects.We":[53],"introduce":[54],"SHAPLENS,":[55],"a":[56,112],"Shapley":[57],"value-based":[58],"attribution":[59],"framework":[60],"using":[61],"Kernel":[62],"SHAP":[63],"and":[64,70,75,89,116,123],"multilayer":[65],"fusion":[66],"detect":[68],"objects.Evaluated":[72],"on":[73,111],"ADE":[74],"COCO":[76],"datasets":[77],"across":[78,106,121],"four":[79],"leading":[80],"VLMs,":[81],"SHAPLENS":[82],"improves":[83],"hallucination":[84],"detection":[85,104],"accuracy":[86],"8-12%":[88],"F1":[90],"10-14%":[92],"over":[93],"the":[94],"best":[95],"baselines.It":[96],"also":[97],"achieves":[98],"up":[99],"6%":[101],"higher":[102],"performance":[105],"three":[107],"distinct":[108],"types":[110],"curated":[113],"HQH":[114],"benchmark":[115],"exhibits":[117],"minimal":[118],"degradation":[119],"(<0.03%)":[120],"partial":[122],"perturbed":[124],"contexts.":[125]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}