{"id":"https://openalex.org/W4389521014","doi":"https://doi.org/10.18653/v1/2023.conll-1.25","title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","display_name":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389521014","doi":"https://doi.org/10.18653/v1/2023.conll-1.25"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.conll-1.25","doi":"https://doi.org/10.18653/v1/2023.conll-1.25","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.conll-1.25","pdf_url":null,"source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","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":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2023.conll-1.25","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023036036","display_name":"Max J. van Duijn","orcid":"https://orcid.org/0000-0003-0798-9598","observed_orcids":["https://orcid.org/0000-0003-0798-9598"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Max van Duijn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bram van Dijk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bram van Dijk","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056156037","display_name":"Tom Kouwenhoven","orcid":"https://orcid.org/0000-0003-2480-4073","observed_orcids":["https://orcid.org/0000-0003-2480-4073"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tom Kouwenhoven","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114107443","display_name":"Werner de Valk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Werner de Valk","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033880574","display_name":"Marco Ren\u00e9 Spruit","orcid":"https://orcid.org/0000-0002-9237-221X","observed_orcids":["https://orcid.org/0000-0002-9237-221X"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marco Spruit","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science","Leiden University Medical Centre"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science","institution_ids":["https://openalex.org/I121797337"]},{"raw_affiliation_string":"Leiden University Medical Centre","institution_ids":["https://openalex.org/I2800006345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008035180","display_name":"Peter van der Putten","orcid":"https://orcid.org/0000-0002-6507-6896","observed_orcids":["https://orcid.org/0000-0002-6507-6896"]},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peter vanderPutten","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.6059,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.99754982,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10258","display_name":"Philosophy and Theoretical Science","score":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/theory-of-mind","display_name":"theory of mind","score":0.9959999918937683},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/false-belief-understanding","display_name":"false belief understanding","score":0.5199999809265137},{"id":"https://openalex.org/keywords/intentionality","display_name":"intentionality","score":0.6399999856948853},{"id":"https://openalex.org/keywords/figurative-language","display_name":"figurative language","score":0.9049999713897705},{"id":"https://openalex.org/keywords/children-s-cognitive-development","display_name":"child cognitive development","score":0.6899999976158142},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.6669999957084656},{"id":"https://openalex.org/keywords/gpt","display_name":"GPT","score":0.6840000152587891},{"id":"https://openalex.org/keywords/cooperative-communication","display_name":"cooperative communication","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C2779560602","wikidata":"https://www.wikidata.org/wiki/Q639219","display_name":"Theory of mind","level":3,"score":0.5612629652023315},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47338834404945374},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4588310420513153},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42452943325042725},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4144289493560791},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.36200809478759766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3297208547592163},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09055611491203308},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2023.conll-1.25","doi":"https://doi.org/10.18653/v1/2023.conll-1.25","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.conll-1.25","pdf_url":null,"source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","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":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.31UKB_LEU:9940749779902711","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3673420","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), p. 389\u2013402","raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:arXiv.org:2310.20320","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.20320","pdf_url":"https://arxiv.org/pdf/2310.20320","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3673420","doi":null,"is_oa":true,"landing_page_url":"https://aclanthology.org/2023.conll-1.25","pdf_url":"https://aclanthology.org/2023.conll-1.25.pdf","source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2310.20320","doi":"https://doi.org/10.48550/arxiv.2310.20320","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.20320","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.conll-1.25","doi":"https://doi.org/10.18653/v1/2023.conll-1.25","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.conll-1.25","pdf_url":null,"source":{"id":"https://openalex.org/S4306418031","display_name":"Conference on Computational Natural Language Learning","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":"Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G755239650","display_name":"Children\u2019s stories as a window into the development of intentional reasoning","funder_award_id":"VI.Veni.191C.051","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1576350636","https://openalex.org/W1963720370","https://openalex.org/W1974955132","https://openalex.org/W1983467315","https://openalex.org/W1993433554","https://openalex.org/W2001771035","https://openalex.org/W2093410327","https://openalex.org/W2106000135","https://openalex.org/W2108248740","https://openalex.org/W2110975890","https://openalex.org/W2116139040","https://openalex.org/W2139188400","https://openalex.org/W2141538250","https://openalex.org/W2171847059","https://openalex.org/W2264742718","https://openalex.org/W2496437279","https://openalex.org/W2503002562","https://openalex.org/W2564010453","https://openalex.org/W2571600439","https://openalex.org/W2579343286","https://openalex.org/W2592312659","https://openalex.org/W2595754429","https://openalex.org/W2625558886","https://openalex.org/W2626778328","https://openalex.org/W2787640378","https://openalex.org/W2889107415","https://openalex.org/W2896457183","https://openalex.org/W2948771346","https://openalex.org/W2969716438","https://openalex.org/W2970536767","https://openalex.org/W3000621992","https://openalex.org/W3006881356","https://openalex.org/W3030163527","https://openalex.org/W3031914912","https://openalex.org/W3133702157","https://openalex.org/W3168771811","https://openalex.org/W3198002980","https://openalex.org/W4223947928","https://openalex.org/W4224308101","https://openalex.org/W4226278401","https://openalex.org/W4230100653","https://openalex.org/W4234782804","https://openalex.org/W4281250694","https://openalex.org/W4307079201","https://openalex.org/W4308760226","https://openalex.org/W4317463334","https://openalex.org/W4318919287","https://openalex.org/W4321277158","https://openalex.org/W4322718191","https://openalex.org/W4323653879","https://openalex.org/W4327810158","https://openalex.org/W4330337479","https://openalex.org/W4360836968","https://openalex.org/W4361020574","https://openalex.org/W4367189299","https://openalex.org/W4376117416","https://openalex.org/W4377121468","https://openalex.org/W4378474033","https://openalex.org/W4378499145","https://openalex.org/W4378908072","https://openalex.org/W4379468930","https://openalex.org/W4379933116","https://openalex.org/W4385430086","https://openalex.org/W4385572854","https://openalex.org/W4387378202","https://openalex.org/W4389519164","https://openalex.org/W4389519950","https://openalex.org/W4391876619","https://openalex.org/W4392681182","https://openalex.org/W4403863303","https://openalex.org/W6931626874","https://openalex.org/W7133189643"],"related_works":["https://openalex.org/W4403863303","https://openalex.org/W7139931220","https://openalex.org/W7131673088","https://openalex.org/W4400032957","https://openalex.org/W4416644609","https://openalex.org/W4403344747","https://openalex.org/W7125508116","https://openalex.org/W4412889608","https://openalex.org/W4399510509","https://openalex.org/W4367189299"],"abstract_inverted_index":{"To":[0],"what":[1,140],"degree":[2],"should":[3],"we":[4,30],"ascribe":[5],"cognitive":[6],"capacities":[7],"to":[8,17,32,47,69,117],"Large":[9],"Language":[10],"Models":[11],"(LLMs),":[12],"such":[13],"as":[14,24],"the":[15,50,94,103,128],"ability":[16],"reason":[18],"about":[19],"intentions":[20],"and":[21,41,58,75,82,109,131,135,151],"beliefs":[22],"known":[23],"Theory":[25],"of":[26,66,89,133],"Mind":[27],"(ToM)?":[28],"Here":[29],"add":[31],"this":[33],"emerging":[34],"debate":[35],"by":[36,155],"(i)":[37],"testing":[38],"11":[39],"base-":[40],"instruction-tuned":[42,100],"LLMs":[43,101],"on":[44,93,161],"capabilities":[45],"relevant":[46],"ToM":[48,119,136,162],"beyond":[49],"dominant":[51],"false-belief":[52],"paradigm,":[53],"including":[54],"non-literal":[55],"language":[56,134],"usage":[57],"recursive":[59],"intentionality;":[60],"(ii)":[61],"using":[62],"newly":[63],"rewritten":[64],"versions":[65],"standardized":[67],"tests":[68],"gauge":[70],"LLMs'":[71],"robustness;":[72],"(iii)":[73],"prompting":[74],"scoring":[76],"for":[77,157],"open":[78],"besides":[79],"closed":[80],"questions;":[81],"(iv)":[83],"benchmarking":[84],"LLM":[85],"performance":[86],"against":[87],"that":[88,99,127,146],"children":[90],"aged":[91],"7-10":[92],"same":[95],"tasks.":[96],"We":[97,125,153],"find":[98],"from":[102],"GPT":[104],"family":[105],"outperform":[106],"other":[107],"models,":[108],"often":[110],"also":[111],"children.":[112],"Base-LLMs":[113],"are":[114],"mostly":[115],"unable":[116],"solve":[118],"tasks,":[120],"even":[121],"with":[122],"specialized":[123],"prompting.":[124],"suggest":[126],"interlinked":[129],"evolution":[130],"development":[132],"may":[137],"help":[138],"explain":[139],"instruction-tuning":[141],"adds:":[142],"rewarding":[143],"cooperative":[144],"communication":[145],"takes":[147],"into":[148],"account":[149],"interlocutor":[150],"context.":[152],"conclude":[154],"arguing":[156],"a":[158],"nuanced":[159],"perspective":[160],"in":[163],"LLMs.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2023-12-11T00:00:00"}