{"id":"https://openalex.org/W4412944598","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1236","title":"Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?","display_name":"Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944598","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1236"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1236","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072785676","display_name":"Simeon Junker","orcid":"https://orcid.org/0009-0003-2529-9213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simeon Junker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069618393","display_name":"Manar Salamah Ali","orcid":"https://orcid.org/0000-0002-4150-3363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manar Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024642806","display_name":"L. Koch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Larissa Koch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078051602","display_name":"Sina Zarrie\u00df","orcid":"https://orcid.org/0000-0002-1384-1218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sina Zarrie\u00df","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064912341","display_name":"Hendrik Buschmeier","orcid":"https://orcid.org/0000-0002-9613-5713"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendrik Buschmeier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.08805167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24101","last_page":"24109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850000143051147,"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/T12031","display_name":"Speech and dialogue systems","score":0.9678000211715698,"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/T10028","display_name":"Topic Modeling","score":0.9125000238418579,"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/computer-science","display_name":"Computer science","score":0.7975292801856995},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.7290210127830505},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5778206586837769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4675793945789337},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46745190024375916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44826140999794006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4399125277996063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975292801856995},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7290210127830505},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5778206586837769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4675793945789337},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46745190024375916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44826140999794006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4399125277996063},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1236","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.11807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11807","pdf_url":"https://arxiv.org/pdf/2506.11807","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.11807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11807","pdf_url":"https://arxiv.org/pdf/2506.11807","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2382521049","https://openalex.org/W1585007175","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W4403053866","https://openalex.org/W2142393343","https://openalex.org/W4411769622"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,28,53],"linguistic":[3],"abilities":[4],"of":[5,52,56,72],"multimodal":[6],"large":[7],"language":[8,36],"models":[9],"in":[10],"reference":[11],"resolution":[12],"tasks":[13],"featuring":[14],"simple":[15],"yet":[16],"abstract":[17],"visual":[18],"stimuli,":[19],"such":[20,68],"as":[21,69],"color":[22,25,73],"patches":[23],"and":[24,60],"grids.":[26],"Although":[27],"task":[29],"may":[30],"not":[31],"seem":[32],"challenging":[33],"for":[34,40,79],"today's":[35],"models,":[37],"being":[38],"straightforward":[39],"human":[41],"dyads,":[42],"we":[43],"consider":[44],"it":[45],"to":[46],"be":[47],"a":[48],"highly":[49],"relevant":[50],"probe":[51],"pragmatic":[54,66],"capabilities":[55],"MLLMs.":[57,81],"Our":[58],"results":[59],"analyses":[61],"indeed":[62],"suggest":[63],"that":[64],"basic":[65],"capabilities,":[67],"context-dependent":[70],"interpretation":[71],"descriptions,":[74],"still":[75],"constitute":[76],"major":[77],"challenges":[78],"state-of-the-art":[80]},"counts_by_year":[],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}
