{"id":"https://openalex.org/W4413145306","doi":"https://doi.org/10.1109/cvpr52734.2025.02757","title":"Vision-Language Models Do Not Understand Negation","display_name":"Vision-Language Models Do Not Understand Negation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145306","doi":"https://doi.org/10.1109/cvpr52734.2025.02757"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5049896090","display_name":"Kumail Alhamoud","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Kumail Alhamoud","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017287975","display_name":"Shaden Alshammari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Shaden Alshammari","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085958820","display_name":"Yonglong Tian","orcid":"https://orcid.org/0000-0002-6110-2145"},"institutions":[{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonglong Tian","raw_affiliation_strings":["OpenAI"],"affiliations":[{"raw_affiliation_string":"OpenAI","institution_ids":["https://openalex.org/I4210161460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100759678","display_name":"Guohao Li","orcid":"https://orcid.org/0000-0003-0260-5129"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guohao Li","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109615038","display_name":"Philip Torr","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip H.S. Torr","raw_affiliation_strings":["University of Oxford"],"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693798","display_name":"Yoon Kim","orcid":"https://orcid.org/0000-0002-4837-8411"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yoon Kim","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070063054","display_name":"Marzyeh Ghassemi","orcid":"https://orcid.org/0000-0001-6349-7251"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Marzyeh Ghassemi","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5049896090"],"corresponding_institution_ids":["https://openalex.org/I4210109586"],"apc_list":null,"apc_paid":null,"fwci":16.7867,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98905106,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"29612","last_page":"29622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8705999851226807,"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/T12031","display_name":"Speech and dialogue systems","score":0.8705999851226807,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.8377000093460083,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8125,"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/negation","display_name":"Negation","score":0.7312349677085876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900732517242432},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5582491159439087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.455281138420105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40039533376693726},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32567447423934937},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.11227697134017944}],"concepts":[{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.7312349677085876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900732517242432},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5582491159439087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.455281138420105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40039533376693726},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32567447423934937},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.11227697134017944}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2059922809","https://openalex.org/W2387527986","https://openalex.org/W2479250593","https://openalex.org/W4283261428","https://openalex.org/W2131148043","https://openalex.org/W2092783274","https://openalex.org/W4318829426","https://openalex.org/W4391025849","https://openalex.org/W4384940451","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Many":[0],"practical":[1],"vision-language":[2,27],"applications":[3],"require":[4],"models":[5,28,130],"that":[6,105,142],"understand":[7,50],"negation,":[8,111],"e.g.,":[9],"when":[10],"using":[11],"natural":[12],"language":[13],"to":[14,35,59,84],"retrieve":[15],"images":[16],"which":[17],"contain":[18],"certain":[19],"objects":[20],"but":[21],"not":[22],"others.":[23],"Despite":[24],"advancements":[25],"in":[26,88,147,151,160],"(VLMs)":[29],"through":[30],"large-scale":[31,132],"training,":[32],"their":[33],"ability":[34],"comprehend":[36],"negation":[37,61,86],"remains":[38],"underexplored.":[39],"This":[40],"study":[41],"addresses":[42],"the":[43],"question:":[44],"how":[45],"well":[46],"do":[47],"current":[48],"VLMs":[49,107],"negation?":[51],"We":[52,140],"introduce":[53],"NegBench,":[54],"a":[55,123,148,157],"new":[56],"benchmark":[57,77],"designed":[58,83],"evaluate":[60,85],"understanding":[62,87],"across":[63],"18":[64],"task":[65],"variations":[66],"and":[67,73,95,156],"79k":[68],"examples":[69],"spanning":[70],"image,":[71],"video,":[72],"medical":[74],"datasets.":[75],"The":[76],"consists":[78],"of":[79,137],"two":[80],"core":[81],"tasks":[82],"diverse":[89],"multimodal":[90],"settings:":[91],"Retrieval":[92],"with":[93,99,110,165],"Negation":[94],"Multiple":[96],"Choice":[97],"Questions":[98],"Negated":[100],"Captions.":[101],"Our":[102],"evaluation":[103],"reveals":[104],"modern":[106],"struggle":[108],"significantly":[109],"often":[112],"performing":[113],"at":[114],"chance":[115],"level.":[116],"To":[117],"address":[118],"these":[119],"shortcomings,":[120],"we":[121,127],"explore":[122],"data-centric":[124],"approach":[125,144],"wherein":[126],"finetune":[128],"CLIP":[129],"on":[131,153,162],"synthetic":[133],"datasets":[134],"containing":[135],"millions":[136],"negated":[138,154,166],"captions.":[139,167],"show":[141],"this":[143],"can":[145],"result":[146],"10%":[149],"increase":[150],"recall":[152],"queries":[155],"28%":[158],"boost":[159],"accuracy":[161],"multiple-choice":[163],"questions":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}