{"id":"https://openalex.org/W7224242533","doi":"https://doi.org/10.18653/2026.emnlp-main.1060","title":"SocialArena: Evaluating Social Intelligence in Large Language Models","display_name":"SocialArena: Evaluating Social Intelligence in Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224242533","doi":"https://doi.org/10.18653/2026.emnlp-main.1060"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1060","doi":"https://doi.org/10.18653/2026.emnlp-main.1060","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1060","pdf_url":"https://aclanthology.org/2026.emnlp-main.1060.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1060.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160122695","display_name":"Zongqi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongqi Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160121121","display_name":"Rui Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102918313","display_name":"Yuchuan Wu","orcid":"https://orcid.org/0009-0004-8389-6101","observed_orcids":["https://orcid.org/0009-0004-8389-6101","https://orcid.org/0009-0000-3657-5859"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchuan Wu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160129613","display_name":"Hua Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Yang","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104202404","display_name":"Bingxue Qiu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingxue Qiu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104211449","display_name":"Tianle Gu","orcid":"https://orcid.org/0009-0005-1546-8196","observed_orcids":["https://orcid.org/0009-0005-1546-8196"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianle Gu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160066673","display_name":"Bing Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Zhao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160115169","display_name":"Yujiu Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiu Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010419481","display_name":"Jieping Ye","orcid":"https://orcid.org/0000-0001-8662-5818","observed_orcids":["https://orcid.org/0000-0001-8662-5818"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160089962","display_name":"Yongbin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbin Li","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24329","last_page":"24355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9330999851226807,"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/T12031","display_name":"Speech and dialogue systems","score":0.9330999851226807,"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":0.010999999940395355,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.009499999694526196,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/social-intelligence","display_name":"social intelligence","score":0.9139999747276306},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9959999918937683},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4350000023841858},{"id":"https://openalex.org/keywords/mental-state-reasoning","display_name":"mental state reasoning","score":0.9430000185966492},{"id":"https://openalex.org/keywords/human-annotators","display_name":"human annotators","score":0.6610000133514404},{"id":"https://openalex.org/keywords/chatbots","display_name":"chatbots","score":0.6389999985694885},{"id":"https://openalex.org/keywords/social-interaction","display_name":"social interaction","score":0.32199999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5149000287055969},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4235000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34139999747276306},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C2779313563","wikidata":"https://www.wikidata.org/wiki/Q17072565","display_name":"On Language","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1060","doi":"https://doi.org/10.18653/2026.emnlp-main.1060","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1060","pdf_url":"https://aclanthology.org/2026.emnlp-main.1060.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2610.39247","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39247","pdf_url":"https://arxiv.org/pdf/2610.39247","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39247","doi":"https://doi.org/10.48550/arxiv.2610.39247","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39247","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1060","doi":"https://doi.org/10.18653/2026.emnlp-main.1060","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1060","pdf_url":"https://aclanthology.org/2026.emnlp-main.1060.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224242533.pdf","grobid_xml":"https://content.openalex.org/works/W7224242533.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2283989780","https://openalex.org/W2936262349","https://openalex.org/W4387561453","https://openalex.org/W4387800437","https://openalex.org/W4402672037","https://openalex.org/W4403579973","https://openalex.org/W4407571828","https://openalex.org/W4412887708","https://openalex.org/W4414281281","https://openalex.org/W4414939355","https://openalex.org/W4415276143","https://openalex.org/W4416615368","https://openalex.org/W4416947242","https://openalex.org/W4417084321","https://openalex.org/W4417136556","https://openalex.org/W7101809050","https://openalex.org/W7123578389","https://openalex.org/W7124715896","https://openalex.org/W7130402983"],"related_works":["https://openalex.org/W4412889731","https://openalex.org/W7224194068","https://openalex.org/W7133198226","https://openalex.org/W4412889592","https://openalex.org/W4411119372","https://openalex.org/W7224594967","https://openalex.org/W7223187308","https://openalex.org/W7133212267","https://openalex.org/W7149313742","https://openalex.org/W103586103"],"abstract_inverted_index":{"We":[0,60],"introduce":[1,130],"SocialArena,":[2],"a":[3,63,88,105,159],"benchmark":[4],"for":[5,96,185],"systematically":[6],"defining":[7],"and":[8,33,80,118,153,157,168,183],"evaluating":[9],"the":[10,131],"social":[11,69,116,139],"intelligence":[12,70],"of":[13,101],"large":[14],"language":[15],"models":[16],"(LLMs).Although":[17],"LLMs":[18],"are":[19],"increasingly":[20],"deployed":[21],"in":[22,104,137],"socially":[23],"interactive":[24],"applications":[25],"such":[26],"as":[27],"mental":[28,77],"health":[29],"counseling,":[30],"companionship":[31],"chatbots,":[32],"educational":[34],"tutoring,":[35],"existing":[36],"evaluations":[37],"remain":[38],"fragmented-focusing":[39],"on":[40],"isolated":[41],"capabilities":[42,103],"or":[43],"single":[44],"scenarios-and":[45],"evaluation":[46,121],"reliability":[47],"is":[48],"largely":[49],"unverified.This":[50],"work":[51],"makes":[52],"three":[53,72],"main":[54],"contributions":[55],"to":[56,126,151],"address":[57],"these":[58,102],"limitations.(1)":[59],"first":[61],"propose":[62],"unified":[64],"three-tier":[65],"framework":[66],"that":[67,107,177],"defines":[68],"along":[71,172],"capability":[73],"dimensions:":[74],"role-playing":[75,89],"ability,":[76],"state":[78],"reasoning,":[79],"behavioral":[81],"reasoning.To":[82],"operationalize":[83],"this":[84],"definition,":[85],"we":[86,129,148],"design":[87],"dialogue":[90],"paradigm":[91],"with":[92,141,173],"explicit":[93],"character":[94],"thinking":[95],"evaluation,":[97,147],"enabling":[98],"simultaneous":[99],"assessment":[100],"manner":[106],"mirrors":[108],"realistic":[109],"human":[110,155],"interactions.(2)":[111],"To":[112,144],"ensure":[113],"diversity":[114],"across":[115],"scenarios":[117],"thereby":[119],"prevent":[120],"conclusions":[122],"from":[123],"being":[124],"confined":[125],"specific":[127],"scenarios,":[128],"U-TRIMF":[132],"framework,":[133],"which":[134],"guides":[135],"us":[136],"synthesizing":[138],"contexts":[140],"broad":[142],"coverage.(3)":[143],"obtain":[145],"reliable":[146],"invest":[149],"$132.4K":[150],"recruit":[152],"train":[154],"annotators":[156,164],"adopt":[158],"human-annotated":[160],"arena-style":[161],"protocol,":[162],"where":[163],"compare":[165],"model":[166],"responses":[167],"provide":[169,180],"preference":[170],"labels":[171],"natural-language":[174],"critiques.We":[175],"hope":[176],"SocialArena":[178],"can":[179],"valuable":[181],"insights":[182],"guidance":[184],"future":[186],"LLM":[187],"improvements.":[188]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-30T00:00:00"}