{"id":"https://openalex.org/W4416036541","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.488","title":"Can Large Language Models Win the International Mathematical Games?","display_name":"Can Large Language Models Win the International Mathematical Games?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036541","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.488"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.488","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.488","pdf_url":"https://aclanthology.org/2025.emnlp-main.488.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.488.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111141237","display_name":"Alessio Cocchieri","orcid":"https://orcid.org/0009-0003-1507-1354"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessio Cocchieri","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046178204","display_name":"Luca Ragazzi","orcid":"https://orcid.org/0000-0003-3574-9962"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Ragazzi","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004842257","display_name":"Giuseppe Tagliavini","orcid":"https://orcid.org/0000-0002-9221-4633"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Tagliavini","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309092","display_name":"Lorenzo Tordi","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Tordi","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080851662","display_name":"Antonella Carbonaro","orcid":"https://orcid.org/0000-0002-3890-4852"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonella Carbonaro","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079648393","display_name":"Gianluca Moro","orcid":"https://orcid.org/0000-0002-3663-7877"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Moro","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Bologna , Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Bologna , Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111141237"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38682799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9656","last_page":"9682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.06239999830722809,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.06239999830722809,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.0502999983727932,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.04729999974370003,"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/natural-language","display_name":"Natural language","score":0.3059999942779541},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.27619999647140503},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2468000054359436},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24570000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5938000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25369998812675476},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2468000054359436},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.23890000581741333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.488","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.488","pdf_url":"https://aclanthology.org/2025.emnlp-main.488.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1048980","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1048980","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.488","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.488","pdf_url":"https://aclanthology.org/2025.emnlp-main.488.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309743","display_name":"Fondazione Cassa di Risparmio in Bologna","ror":"https://ror.org/0404v4f94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036541.pdf","grobid_xml":"https://content.openalex.org/works/W4416036541.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,14,43,64],"large":[3],"language":[4],"models":[5,19],"(LLMs)":[6],"have":[7],"demonstrated":[8],"strong":[9],"mathematical":[10,58,72,89],"reasoning":[11,92],"abilities,":[12],"even":[13],"visual":[15],"contexts,":[16],"with":[17],"some":[18,108],"surpassing":[20],"human":[21,41,103],"performance":[22,42],"on":[23],"existing":[24],"benchmarks.However,":[25],"these":[26,47],"benchmarks":[27],"lack":[28],"structured":[29,85],"age":[30,76],"categorization,":[31],"clearly":[32],"defined":[33],"skill":[34],"requirements,":[35],"and-crucially-were":[36],"not":[37],"designed":[38],"to":[39,124],"assess":[40],"international":[44,71],"competitions.To":[45],"address":[46],"limitations,":[48],"we":[49],"introduce":[50],"MATHGAMES,":[51],"a":[52,79,84,96],"new":[53],"benchmark":[54],"of":[55,87,109],"2,183":[56],"high-quality":[57],"problems":[59],"(both":[60],"text-only":[61],"and":[62,78,90,102],"multimodal)":[63],"an":[65,70],"openended":[66],"format,":[67],"sourced":[68],"from":[69],"games":[73],"championships.Spanning":[74],"seven":[75],"groups":[77],"skill-based":[80],"taxonomy,":[81],"MATHGAMES":[82],"enables":[83],"evaluation":[86],"LLMs'":[88],"logical":[91],"abilities.Our":[93],"experiments":[94],"reveal":[95],"substantial":[97],"gap":[98],"between":[99],"state-of-theart":[100],"LLMs":[101],"participants-even":[104],"11year-olds":[105],"consistently":[106],"outperform":[107],"the":[110,113],"strongest":[111],"models-highlighting":[112],"need":[114],"for":[115],"advancements.Further,":[116],"our":[117],"detailed":[118],"error":[119],"analysis":[120],"offers":[121],"valuable":[122],"insights":[123],"guide":[125],"future":[126],"research.The":[127],"data":[128],"is":[129],"publicly":[130],"available":[131],"at":[132],"https://":[133],"disi-unibo-nlp.github.io/math-games/.":[134]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-11-08T00:00:00"}