{"id":"https://openalex.org/W4416036101","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.12","title":"LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts","display_name":"LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036101","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.12"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.12","pdf_url":"https://aclanthology.org/2025.findings-emnlp.12.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.12.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036309113","display_name":"Junhao Chen","orcid":"https://orcid.org/0000-0001-8072-4065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024567788","display_name":"Jingbo Sun","orcid":"https://orcid.org/0000-0003-4462-8660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingbo Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394772","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-4962-002X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113156004","display_name":"Haidong Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haidong Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhao Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110886894","display_name":"Yibin Xu","orcid":"https://orcid.org/0000-0002-2211-5533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibin Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025049450","display_name":"Hao Zhao","orcid":"https://orcid.org/0000-0001-7903-581X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhao","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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.14499999582767487,"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":0.14499999582767487,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.051100000739097595,"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/T13629","display_name":"Text Readability and Simplification","score":0.0478999987244606,"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/benchmark","display_name":"Benchmark (surveying)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.310699999332428},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3043999969959259},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.29170000553131104},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28209999203681946},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2736000120639801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538000106811523},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41609999537467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.12","pdf_url":"https://aclanthology.org/2025.findings-emnlp.12.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.12","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.12","pdf_url":"https://aclanthology.org/2025.findings-emnlp.12.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036101.pdf","grobid_xml":"https://content.openalex.org/works/W4416036101.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"advance":[5],"across":[6,91],"diverse":[7],"tasks,":[8],"the":[9],"need":[10],"for":[11,98],"comprehensive":[12],"evaluation":[13,40],"beyond":[14],"single":[15],"metrics":[16],"becomes":[17],"increasingly":[18],"important.To":[19],"fully":[20],"assess":[21],"LLM":[22],"intelligence,":[23,102],"it":[24],"is":[25],"crucial":[26],"to":[27,58],"examine":[28],"their":[29,108],"interactive":[30],"dynamics":[31],"and":[32,47,69,74,81,88,106,115],"strategic":[33,60,82,101],"behaviors.We":[34],"present":[35],"LLMsPark,":[36],"a":[37,55,95],"game":[38],"theory-based":[39],"platform":[41],"that":[42],"measures":[43],"LLMs'":[44,100],"decision-making":[45],"strategies":[46],"social":[48],"behaviors":[49],"in":[50,110],"classic":[51],"game-theoretic":[52,112],"settings,":[53],"providing":[54],"multi-agent":[56],"environment":[57],"explore":[59],"depth.Our":[61],"system":[62],"cross-evaluates":[63],"15":[64],"leading":[65],"LLMs":[66],"(both":[67],"commercial":[68],"opensource)":[70],"using":[71],"leaderboard":[72],"rankings":[73,116],"scoring":[75],"mechanisms.Higher":[76],"scores":[77],"reflect":[78],"stronger":[79],"reasoning":[80],"capabilities,":[83],"revealing":[84],"distinct":[85],"behavioral":[86],"patterns":[87],"performance":[89],"differences":[90],"models.This":[92],"work":[93],"introduces":[94],"novel":[96],"perspective":[97],"evaluating":[99],"enriching":[103],"existing":[104],"benchmarks":[105],"broadening":[107],"assessment":[109],"interactive,":[111],"scenarios.The":[113],"benchmark":[114],"are":[117],"publicly":[118],"available":[119],"at":[120],"https://llmsparks.github.io/.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}