{"id":"https://openalex.org/W7133838681","doi":"https://doi.org/10.48550/arxiv.2603.04161","title":"Traces of Social Competence in Large Language Models","display_name":"Traces of Social Competence in Large Language Models","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133838681","doi":"https://doi.org/10.48550/arxiv.2603.04161"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04161","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.04161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128217671","display_name":"Tom Kouwenhoven","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kouwenhoven, Tom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128215837","display_name":"Michiel van der Meer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van der Meer, Michiel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074362392","display_name":"Max J. van Duijn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van Duijn, Max","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1768999993801117,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1768999993801117,"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/T10656","display_name":"Child and Animal Learning Development","score":0.09969999641180038,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.07360000163316727,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6031000018119812},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4578000009059906},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43860000371932983},{"id":"https://openalex.org/keywords/competence","display_name":"Competence (human resources)","score":0.43810001015663147},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4320000112056732},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/item-response-theory","display_name":"Item response theory","score":0.40860000252723694},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.38269999623298645}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5230000019073486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5088000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5087000131607056},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.38269999623298645},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C181447626","wikidata":"https://www.wikidata.org/wiki/Q1224359","display_name":"Differential item functioning","level":4,"score":0.2824999988079071},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C2778638050","wikidata":"https://www.wikidata.org/wiki/Q5421252","display_name":"Explanatory model","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C17601614","wikidata":"https://www.wikidata.org/wiki/Q1346205","display_name":"Linguistic competence","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C86658582","wikidata":"https://www.wikidata.org/wiki/Q1432778","display_name":"Social cognition","level":3,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04161","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.04161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04161","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.737607479095459,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"False":[1],"Belief":[2],"Test":[3],"(FBT)":[4],"has":[5],"been":[6],"the":[7,25,169],"main":[8],"method":[9],"for":[10],"assessing":[11],"Theory":[12],"of":[13,30,61,172],"Mind":[14],"(ToM)":[15],"and":[16,27,45,78],"related":[17],"socio-cognitive":[18,81],"competencies.":[19],"For":[20],"Large":[21],"Language":[22],"Models":[23],"(LLMs),":[24],"reliability":[26],"explanatory":[28],"potential":[29],"this":[31,112,135],"test":[32],"have":[33],"remained":[34],"limited":[35],"due":[36],"to":[37,73,149,163],"issues":[38,51],"like":[39],"data":[40],"contamination,":[41],"insufficient":[42],"model":[43,76,87],"details,":[44],"inconsistent":[46],"controls.":[47],"We":[48,83],"address":[49],"these":[50],"by":[52],"testing":[53],"17":[54],"open-weight":[55],"models":[56,143],"on":[57],"a":[58,121,165],"balanced":[59],"set":[60],"192":[62],"FBT":[63,174],"variants":[64],"(Trott":[65],"et":[66],"al.,":[67],"2023)":[68],"using":[69],"Bayesian":[70],"Logistic":[71],"regression":[72],"identify":[74],"how":[75],"size":[77,88],"post-training":[79],"affect":[80],"competence.":[82],"find":[84],"that":[85,98,134,142,152],"scaling":[86],"benefits":[89],"performance,":[90],"but":[91,114],"not":[92],"strictly.":[93],"A":[94],"cross-over":[95,136],"effect":[96,137],"reveals":[97],"explicating":[99],"propositional":[100],"attitudes":[101],"(X":[102],"thinks)":[103],"fundamentally":[104],"alters":[105],"response":[106,146],"patterns.":[107],"Instruction":[108],"tuning":[109],"partially":[110],"mitigates":[111],"effect,":[113],"further":[115],"reasoning-oriented":[116],"fine-tuning":[117],"amplifies":[118],"it.":[119],"In":[120],"case":[122],"study":[123],"analysing":[124],"social":[125],"reasoning":[126],"ability":[127],"throughout":[128],"OLMo":[129],"2":[130],"training,":[131],"we":[132],"show":[133],"emerges":[138],"during":[139],"pre-training,":[140],"suggesting":[141],"acquire":[144],"stereotypical":[145],"patterns":[147],"tied":[148],"mental-state":[150],"vocabulary":[151],"can":[153],"outweigh":[154],"other":[155],"scenario":[156],"semantics.":[157],"Finally,":[158],"vector":[159,167],"steering":[160],"allows":[161],"us":[162],"isolate":[164],"think":[166],"as":[168],"causal":[170],"driver":[171],"observed":[173],"behaviour.":[175]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-03-06T00:00:00"}