{"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","doi":"https://doi.org/10.1109/cvpr52734.2025.02757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02757","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.09425","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049896090","display_name":"Kumail Alhamoud","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kumail Alhamoud","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017287975","display_name":"Shaden Alshammari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaden Alshammari","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085958820","display_name":"Yonglong Tian","orcid":"https://orcid.org/0000-0002-6110-2145","observed_orcids":["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"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0003-0260-5129","https://orcid.org/0009-0002-7072-1324","https://orcid.org/0009-0003-8057-7343"]},"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"],"raw_orcid":null,"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 H.S. Torr","orcid":"https://orcid.org/0000-0001-5545-7217","observed_orcids":["https://orcid.org/0000-0001-5545-7217"]},"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"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0002-4837-8411"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoon Kim","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070063054","display_name":"Marzyeh Ghassemi","orcid":"https://orcid.org/0000-0001-6349-7251","observed_orcids":["https://orcid.org/0000-0001-6349-7251"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marzyeh Ghassemi","raw_affiliation_strings":["MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.4215,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.99283753,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.9919999837875366},{"id":"https://openalex.org/keywords/multiple-choice-questions","display_name":"multiple-choice questions","score":0.6480000019073486},{"id":"https://openalex.org/keywords/medical-image-retrieval","display_name":"medical image retrieval","score":0.4779999852180481}],"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":4,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02757","doi":"https://doi.org/10.1109/cvpr52734.2025.02757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02757","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:dbc61afb-7ace-41f8-983c-697fea9ce550","doi":null,"is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:dbc61afb-7ace-41f8-983c-697fea9ce550/files/ss1784p187","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:arXiv.org:2501.09425","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.09425","pdf_url":"https://arxiv.org/pdf/2501.09425","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.09425","doi":"https://doi.org/10.48550/arxiv.2501.09425","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.09425","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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.09425","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.09425","pdf_url":"https://arxiv.org/pdf/2501.09425","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4770447474","display_name":"CAREER: Ethical Machine Learning in Health: Robustness in Data, Learning and Deployment","funder_award_id":"2339381","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6505763180","display_name":null,"funder_award_id":"EP/W002981/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413145306.pdf","grobid_xml":"https://content.openalex.org/works/W4413145306.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2982596739","https://openalex.org/W4285606530","https://openalex.org/W4323066559","https://openalex.org/W4391591725","https://openalex.org/W4393399880","https://openalex.org/W4401306886","https://openalex.org/W4413144796"],"related_works":["https://openalex.org/W4412888723","https://openalex.org/W7172121908","https://openalex.org/W4416459102","https://openalex.org/W7140186782","https://openalex.org/W4409262921","https://openalex.org/W4393399880","https://openalex.org/W7163651261","https://openalex.org/W7147276921","https://openalex.org/W7155215847","https://openalex.org/W7222646479"],"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":35},{"year":2025,"cited_by_count":16}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}