{"id":"https://openalex.org/W4414959212","doi":"https://doi.org/10.1145/3717511.3747081","title":"Evaluating Theory-of-Mind in Large Language Models Through Opponent Modeling","display_name":"Evaluating Theory-of-Mind in Large Language Models Through Opponent Modeling","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4414959212","doi":"https://doi.org/10.1145/3717511.3747081"},"language":"en","primary_location":{"id":"doi:10.1145/3717511.3747081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3717511.3747081","pdf_url":null,"source":null,"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 25th ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3717511.3747081","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062505189","display_name":"Emre Kuru","orcid":"https://orcid.org/0009-0007-6130-6272"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Emre Kuru","raw_affiliation_strings":["\u00d6zyegin University, Istanbul, Turkiye"],"raw_orcid":"https://orcid.org/0009-0007-6130-6272","affiliations":[{"raw_affiliation_string":"\u00d6zyegin University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058381002","display_name":"An\u0131l Do\u011fru","orcid":"https://orcid.org/0000-0002-9951-8912"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"An\u0131l Do\u011fru","raw_affiliation_strings":["\u00d6zyegin University, Istanbul, Turkiye"],"raw_orcid":"https://orcid.org/0000-0002-9951-8912","affiliations":[{"raw_affiliation_string":"\u00d6zyegin University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Merve Do\u011fan","orcid":"https://orcid.org/0009-0003-8595-2085"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Merve Do\u011fan","raw_affiliation_strings":["\u00d6zyegin University, Istanbul, Turkiye"],"raw_orcid":"https://orcid.org/0009-0003-8595-2085","affiliations":[{"raw_affiliation_string":"\u00d6zyegin University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011208990","display_name":"Reyhan Aydo\u011fan","orcid":"https://orcid.org/0000-0002-5260-9999"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Reyhan Aydo\u011fan","raw_affiliation_strings":["Artificial Intelligence and Data Engineering, \u00d6zyegin University, Istanbul, Turkiye and Interactive Intelligence Group, Delft University Of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5260-9999","affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Data Engineering, \u00d6zyegin University, Istanbul, Turkiye and Interactive Intelligence Group, Delft University Of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062505189"],"corresponding_institution_ids":["https://openalex.org/I44925452"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14036779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9909999966621399,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9890000224113464,"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/negotiation","display_name":"Negotiation","score":0.6715999841690063},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.6557000279426575},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5227000117301941},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4413999915122986},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.39100000262260437},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.6715999841690063},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6557000279426575},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.527400016784668},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3456999957561493},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3717511.3747081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3717511.3747081","pdf_url":null,"source":null,"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 25th ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/11249","is_oa":true,"landing_page_url":"https://hdl.handle.net/10679/11249","pdf_url":null,"source":null,"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3717511.3747081","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3717511.3747081","pdf_url":null,"source":null,"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 25th ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1529944193","https://openalex.org/W1777811955","https://openalex.org/W1979354511","https://openalex.org/W2046002826","https://openalex.org/W2084680666","https://openalex.org/W2103762770","https://openalex.org/W2105440797","https://openalex.org/W2139512434","https://openalex.org/W2141538250","https://openalex.org/W2591673867","https://openalex.org/W2605150730","https://openalex.org/W2741983168","https://openalex.org/W2761697333","https://openalex.org/W2930957955","https://openalex.org/W3082574219","https://openalex.org/W3173562877","https://openalex.org/W3188546119","https://openalex.org/W3214664326","https://openalex.org/W4292402161","https://openalex.org/W4309663019","https://openalex.org/W4387126705","https://openalex.org/W4388294229","https://openalex.org/W4401023657","https://openalex.org/W4401024282","https://openalex.org/W4402404957","https://openalex.org/W4404781718","https://openalex.org/W4405833319","https://openalex.org/W4408931386"],"related_works":[],"abstract_inverted_index":{"Theory-of-Mind":[0,146],"(ToM),":[1],"the":[2,6,37,68],"ability":[3],"to":[4,73],"infer":[5,59,78],"mental":[7],"states,":[8],"goals,":[9],"and":[10,51,77,84,110,136],"preferences":[11,62,109],"of":[12,19,39,92,129],"others":[13],"-":[14],"is":[15],"a":[16,49,56,89,141],"core":[17],"component":[18],"human":[20],"social":[21,134],"intelligence.":[22],"In":[23],"this":[24],"work,":[25],"we":[26],"investigate":[27],"whether":[28],"Large":[29],"Language":[30],"Models":[31],"(LLMs)":[32],"exhibit":[33],"ToM":[34,53],"capabilities":[35],"in":[36,46,111,147],"context":[38],"strategic":[40],"interaction.":[41],"We":[42,70,87],"frame":[43],"opponent":[44,117,138],"modeling":[45,118,139],"negotiation":[47,97],"as":[48,140],"grounded":[50],"interpretable":[52],"task,":[54],"where":[55],"model":[57],"must":[58],"an":[60],"agent's":[61],"by":[63],"observing":[64],"offer":[65,75,126],"exchanges":[66],"during":[67],"negotiation.":[69],"guide":[71],"LLMs":[72,94,103],"interpret":[74],"histories":[76],"latent":[79],"utility":[80],"representations,":[81],"including":[82],"issue":[83],"value":[85],"weights.":[86],"conduct":[88],"comprehensive":[90],"evaluation":[91],"state-of-the-art":[93],"across":[95],"multiple":[96],"domains.":[98],"Our":[99],"results":[100],"show":[101],"that":[102],"can":[104],"successfully":[105],"recover":[106],"opponents":[107],"unknown":[108],"some":[112],"cases":[113],"even":[114,120],"outperform":[115],"classical":[116],"base-lines,":[119],"without":[121],"task-specific":[122],"training.":[123],"These":[124],"findings":[125],"new":[127],"evidence":[128],"LLMs'":[130],"emerging":[131],"capacity":[132],"for":[133,144],"reasoning":[135],"position":[137],"practical":[142],"benchmark":[143],"evaluating":[145],"foundation":[148],"models.":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}