{"id":"https://openalex.org/W7126382208","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.101","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","display_name":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126382208","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.101"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.101","pdf_url":"https://aclanthology.org/2024.findings-eacl.101.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.101.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124517234","display_name":"Martha Lewis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martha Lewis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124677382","display_name":"Nihal Nayak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nihal Nayak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000507166","display_name":"Peilin Yu","orcid":"https://orcid.org/0000-0001-8688-5396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peilin Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062612448","display_name":"Jack Merullo","orcid":"https://orcid.org/0009-0005-9673-6809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jack Merullo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109664262","display_name":"Qinan Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinan Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011117177","display_name":"Stephen H. Bach","orcid":"https://orcid.org/0000-0003-3857-3560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen Bach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053850863","display_name":"Ellie Pavlick","orcid":"https://orcid.org/0000-0002-7155-5420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ellie Pavlick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2008,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79524753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1487","last_page":"1500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.07410000264644623,"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"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.07410000264644623,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.040300000458955765,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.025599999353289604,"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/image","display_name":"Image (mathematics)","score":0.5400000214576721},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.366100013256073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3546999990940094},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.3303999900817871},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.32339999079704285}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5593000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5471000075340271},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47510001063346863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2606000006198883},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.101","pdf_url":"https://aclanthology.org/2024.findings-eacl.101.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.101","pdf_url":"https://aclanthology.org/2024.findings-eacl.101.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1891423586","display_name":null,"funder_award_id":"FA8750-19-2-1006","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126382208.pdf","grobid_xml":"https://content.openalex.org/works/W7126382208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"neural":[1],"network":[2],"models":[3,24,101],"combining":[4],"text":[5],"and":[6,47,61,69,126],"images":[7],"have":[8],"made":[9],"incredible":[10],"progress":[11],"in":[12,73,139,144],"recent":[13],"years.However,":[14],"it":[15],"remains":[16],"an":[17],"open":[18],"question":[19],"to":[20,65,70,109,129],"what":[21],"extent":[22],"such":[23,35],"encode":[25,66],"compositional":[26,67,98,112],"representations":[27],"of":[28,56,89,105],"the":[29,44,54,87,154],"concepts":[30,68,138],"over":[31,43],"which":[32],"they":[33],"operate,":[34],"as":[36],"correctly":[37],"identifying":[38],"red":[39,46],"cube":[40,79],"by":[41],"reasoning":[42],"constituents":[45],"cube.In":[48],"this":[49],"work,":[50],"we":[51,91],"focus":[52],"on":[53,97,120],"ability":[55],"a":[57,74,103,140],"large":[58],"pretrained":[59],"vision":[60],"language":[62],"model":[63],"(CLIP)":[64],"bind":[71],"variables":[72],"structure-sensitive":[75],"way":[76],"(e.g.,":[77],"differentiating":[78],"behind":[80,84],"sphere":[81,83],"from":[82,95],"cube).To":[85],"inspect":[86],"performance":[88,151,163],"CLIP,":[90],"compare":[92],"several":[93],"architectures":[94],"research":[96,106],"distributional":[99],"semantics":[100],"(CDSMs),":[102],"line":[104],"that":[107,134],"attempts":[108],"implement":[110],"traditional":[111],"linguistic":[113],"structures":[114],"within":[115],"embedding":[116],"spaces.We":[117],"benchmark":[118],"them":[119],"three":[121],"synthetic":[122],"datasets":[123],"-singleobject,":[124],"two-object,":[125],"relational":[127],"-designed":[128],"test":[130],"concept":[131,147],"binding.We":[132],"find":[133],"CLIP":[135],"can":[136],"compose":[137],"single-object":[141],"setting,":[142],"but":[143],"situations":[145],"where":[146],"binding":[148],"is":[149],"needed,":[150],"drops":[152],"dramatically.At":[153],"same":[155],"time,":[156],"CDSMs":[157],"also":[158],"perform":[159],"poorly,":[160],"with":[161],"best":[162],"at":[164],"chance":[165],"level.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2026-02-02T00:00:00"}