{"id":"https://openalex.org/W7166872078","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2081","title":"Grounded Concreteness: Human-Like Concreteness Sensitivity in Vision\u2013Language Models","display_name":"Grounded Concreteness: Human-Like Concreteness Sensitivity in Vision\u2013Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166872078","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2081"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2081","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2081","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2081","pdf_url":"https://aclanthology.org/2026.findings-acl.2081.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"Findings of the Association for Computational Linguistics: ACL 2026","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.findings-acl.2081.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123953830","display_name":"Aryan Roy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aryan Roy","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139736843","display_name":"Zekun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zekun Wang","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123885553","display_name":"Christopher J. MacLellan","orcid":"https://orcid.org/0000-0003-3084-5189","observed_orcids":["https://orcid.org/0000-0003-3084-5189"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J. MacLellan","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48980149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41934","last_page":"41950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.00039999998989515007,"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/T10181","display_name":"Natural Language Processing Techniques","score":9.999999747378752e-05,"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/vision-language-models","display_name":"vision-language models","score":0.906000018119812},{"id":"https://openalex.org/keywords/perceptual-grounding","display_name":"perceptual grounding","score":0.6959999799728394},{"id":"https://openalex.org/keywords/embedding-geometry","display_name":"embedding geometry","score":0.8970000147819519},{"id":"https://openalex.org/keywords/attention-dynamics","display_name":"attention dynamics","score":0.7910000085830688},{"id":"https://openalex.org/keywords/human-alignment","display_name":"human alignment","score":0.4519999921321869},{"id":"https://openalex.org/keywords/multimodal-pretraining","display_name":"multimodal pre-training","score":0.8450000286102295}],"concepts":[{"id":"https://openalex.org/C2778436841","wikidata":"https://www.wikidata.org/wiki/Q5159081","display_name":"Concreteness","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42649999260902405},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29820001125335693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26969999074935913},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2081","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2081","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2081","pdf_url":"https://aclanthology.org/2026.findings-acl.2081.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2081","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2081","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2081","pdf_url":"https://aclanthology.org/2026.findings-acl.2081.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"Findings of the Association for Computational Linguistics: ACL 2026","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/W7166872078.pdf","grobid_xml":"https://content.openalex.org/works/W7166872078.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162574141","https://openalex.org/W4403051422","https://openalex.org/W4415329277","https://openalex.org/W4416034100","https://openalex.org/W7153978741","https://openalex.org/W7128064278","https://openalex.org/W7154733047","https://openalex.org/W7206161854","https://openalex.org/W2771263905","https://openalex.org/W7161454151"],"abstract_inverted_index":{"Do":[0],"vision-language":[1],"models":[2,15,108],"(VLMs)":[3],"develop":[4],"more":[5,121,132],"human-like":[6],"sensitivity":[7],"to":[8,57,75,112],"linguistic":[9],"concreteness":[10,62,74,88,105],"than":[11,55],"text-only":[12],"large":[13],"language":[14],"(LLMs)":[16],"when":[17],"both":[18],"are":[19],"evaluated":[20],"with":[21,27,153],"textonly":[22],"prompts?We":[23],"study":[24],"this":[25],"question":[26],"a":[28,87],"controlled":[29],"comparison":[30],"between":[31],"matched":[32],"Llama":[33,38],"text":[34],"backbones":[35],"and":[36,90,109,125,146],"their":[37],"Vision":[39],"counterparts":[40],"across":[41],"multiple":[42],"model":[43],"scales,":[44,126],"treating":[45],"multimodal":[46,118],"pretraining":[47],"as":[48],"an":[49],"ablation":[50],"on":[51,131],"perceptual":[52],"grounding":[53],"rather":[54],"access":[56],"images":[58],"at":[59,64],"inference.We":[60],"measure":[61],"effects":[63],"three":[65],"complementary":[66],"levels:":[67],"(i)":[68],"output":[69],"behavior,":[70],"by":[71,81,94],"relating":[72],"question-level":[73],"QA":[76],"accuracy;":[77],"(ii)":[78],"embedding":[79],"geometry,":[80],"testing":[82,116],"whether":[83,117],"representations":[84],"organize":[85],"along":[86],"axis;":[89],"(iii)":[91],"attention":[92,150],"dynamics,":[93],"quantifying":[95],"context":[96],"reliance":[97],"via":[98],"attention-entropy":[99],"measures.In":[100],"addition,":[101],"we":[102],"elicit":[103],"token-level":[104],"ratings":[106,140],"from":[107],"evaluate":[110],"alignment":[111],"human":[113,144],"norm":[114],"distributions,":[115],"training":[119],"yields":[120],"human-consistent":[122],"judgments.Across":[123],"benchmarks":[124],"VLMs":[127],"show":[128],"larger":[129],"gains":[130],"concrete":[133],"inputs,":[134],"exhibit":[135],"clearer":[136],"concreteness-structured":[137],"representations,":[138],"produce":[139],"that":[141],"better":[142],"match":[143],"norms,":[145],"display":[147],"systematically":[148],"different":[149],"patterns":[151],"consistent":[152],"increased":[154],"grounding.":[155]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}