{"id":"https://openalex.org/W4417341952","doi":"https://doi.org/10.18653/v1/2026.acl-long.712","title":"VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models","display_name":"VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417341952","doi":"https://doi.org/10.18653/v1/2026.acl-long.712"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.712","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.712","pdf_url":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050447573","display_name":"Chahat Raj","orcid":"https://orcid.org/0000-0003-0083-6812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chahat Raj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101246368","display_name":"Bowen Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101545719","display_name":"Aylin Caliskan","orcid":"https://orcid.org/0000-0001-7154-8629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aylin Caliskan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019994221","display_name":"Ziwei Zhu","orcid":"https://orcid.org/0000-0002-3990-4774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziwei Zhu","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03260232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15645","last_page":"15673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6895999908447266,"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":0.6895999908447266,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.07190000265836716,"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"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.032999999821186066,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5705999732017517},{"id":"https://openalex.org/keywords/trait","display_name":"Trait","score":0.5608999729156494},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5008999705314636},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4957999885082245}],"concepts":[{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5680000185966492},{"id":"https://openalex.org/C106934330","wikidata":"https://www.wikidata.org/wiki/Q1971873","display_name":"Trait","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.5389999747276306},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C98447023","wikidata":"https://www.wikidata.org/wiki/Q1540351","display_name":"Social identity theory","level":3,"score":0.38600000739097595},{"id":"https://openalex.org/C130064352","wikidata":"https://www.wikidata.org/wiki/Q853725","display_name":"Social relation","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25859999656677246},{"id":"https://openalex.org/C163877629","wikidata":"https://www.wikidata.org/wiki/Q2642673","display_name":"Social constructionism","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.712","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.712","pdf_url":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.22897","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.22897","pdf_url":"https://arxiv.org/pdf/2505.22897","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.22897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.22897","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.712","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.712","pdf_url":null,"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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"bias":[1,22,56],"in":[2,11,57,81],"large":[3],"language":[4],"models":[5,13,86],"(LLMs)":[6],"is":[7],"well-studied,":[8],"similar":[9],"concerns":[10],"vision-language":[12],"(VLMs)":[14],"have":[15],"received":[16],"comparatively":[17],"less":[18],"attention.":[19],"Existing":[20],"VLM":[21],"studies":[23],"often":[24],"focus":[25],"on":[26],"portrait-style":[27],"images":[28,53],"and":[29,34,39,69,89,92,111,125],"gender-occupation":[30],"associations,":[31],"overlooking":[32],"broader":[33],"more":[35],"complex":[36],"social":[37,99,115,135],"stereotypes":[38],"their":[40],"implied":[41],"harm.":[42],"This":[43],"work":[44],"introduces":[45],"VIGNETTE,":[46],"a":[47,60],"large-scale":[48],"VQA":[49],"benchmark":[50],"with":[51],"30M+":[52],"for":[54],"evaluating":[55],"VLMs":[58,78,104,133],"through":[59,117],"question-answering":[61],"framework":[62],"spanning":[63],"four":[64],"directions:":[65],"factuality,":[66],"perception,":[67],"stereotyping,":[68],"decision":[70],"making.":[71],"Beyond":[72],"narrowly-centered":[73],"studies,":[74],"we":[75,101],"assess":[76],"how":[77,85,103,132],"interpret":[79],"identities":[80],"contextualized":[82],"settings,":[83],"revealing":[84],"make":[87],"trait":[88,110],"capability":[90],"assumptions":[91],"exhibit":[93],"patterns":[94],"of":[95],"discrimination.":[96],"Drawing":[97],"from":[98,137],"psychology,":[100],"examine":[102],"connect":[105],"visual":[106],"identity":[107],"cues":[108],"to":[109],"role-based":[112],"inferences,":[113],"encoding":[114],"hierarchies,":[116],"biased":[118],"selections.":[119],"Our":[120],"findings":[121],"uncover":[122],"subtle,":[123],"multifaceted,":[124],"surprising":[126],"stereotypical":[127],"patterns,":[128],"offering":[129],"insights":[130],"into":[131],"construct":[134],"meaning":[136],"inputs.":[138]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
