{"id":"https://openalex.org/W4412945328","doi":"https://doi.org/10.18653/v1/2025.acl-long.699","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","display_name":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945328","doi":"https://doi.org/10.18653/v1/2025.acl-long.699"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.699","doi":"https://doi.org/10.18653/v1/2025.acl-long.699","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.699","pdf_url":"https://aclanthology.org/2025.acl-long.699.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.acl-long.699.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028962243","display_name":"Guijin Son","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guijin Son","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012954217","display_name":"Jiwoo Hong","orcid":"https://orcid.org/0000-0002-2226-597X","observed_orcids":["https://orcid.org/0000-0002-2226-597X"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwoo Hong","raw_affiliation_strings":["KAIST AI MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI MODULABS","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088036513","display_name":"Hyunwoo Ko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo Ko","raw_affiliation_strings":["KAIST AI MODULABS","Yonsei University OneLineAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI MODULABS","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Yonsei University OneLineAI","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":null,"display_name":"James Thorne","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"James Thorne","raw_affiliation_strings":["KAIST AI MODULABS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST AI MODULABS","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2747,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84864262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"14333","last_page":"14368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.6371999979019165,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.6371999979019165,"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/T14025","display_name":"Educational Technology and Assessment","score":0.07900000363588333,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12522","display_name":"Mathematics Education and Pedagogy","score":0.041099999099969864,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/test-time-scaling","display_name":"test-time scaling","score":0.9570000171661377},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.9539999961853027},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.3709999918937683},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5649999976158142},{"id":"https://openalex.org/keywords/mathematical-problem-solving","display_name":"mathematical problem solving","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.903038501739502},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.664063036441803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.605170726776123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5329742431640625},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5205805897712708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45079803466796875},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3734424114227295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22370317578315735},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14964225888252258},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12400877475738525},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.699","doi":"https://doi.org/10.18653/v1/2025.acl-long.699","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.699","pdf_url":"https://aclanthology.org/2025.acl-long.699.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.17407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.17407","pdf_url":"https://arxiv.org/pdf/2502.17407","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.2502.17407","doi":"https://doi.org/10.48550/arxiv.2502.17407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.17407","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/v1/2025.acl-long.699","doi":"https://doi.org/10.18653/v1/2025.acl-long.699","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.699","pdf_url":"https://aclanthology.org/2025.acl-long.699.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3736587842","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4468082379","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5278263090","display_name":null,"funder_award_id":"RS-2024-00398115","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7102533171","display_name":null,"funder_award_id":"RS-2024-00398115","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945328.pdf","grobid_xml":"https://content.openalex.org/works/W4412945328.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7139038209","https://openalex.org/W4407092048","https://openalex.org/W4415329122","https://openalex.org/W7154488222","https://openalex.org/W4415328803","https://openalex.org/W4416091731","https://openalex.org/W7158890012","https://openalex.org/W7213478981","https://openalex.org/W4416060352","https://openalex.org/W4415025609"],"abstract_inverted_index":{"Scaling":[0],"pre-training":[1],"compute":[2],"has":[3],"proven":[4],"effective":[5],"for":[6,14,57],"achieving":[7],"multilinguality,":[8],"but":[9],"does":[10],"the":[11,129],"same":[12],"hold":[13],"test-time":[15,34,131,137],"scaling?In":[16],"this":[17],"work,":[18],"we":[19,55,86,134,150],"introduce":[20],"MCLM,":[21,73,152],"a":[22,52,68,110,119],"multilingual":[23,53,145],"math":[24],"benchmark":[25],"featuring":[26],"competition-level":[27],"problems":[28],"in":[29],"55":[30],"languages.We":[31],"test":[32],"three":[33],"scaling":[35,95,132,138],"methods-Outcome":[36],"Reward":[37,41],"Modeling":[38,42],"(ORM),":[39],"Process":[40],"(PRM),":[43],"and":[44,50,154],"Budget":[45],"Forcing":[46],"(BF)-on":[47],"both":[48],"Qwen2.5-1.5BMath":[49,64],"MR1-1.5B,":[51,153],"LLM":[54],"trained":[56],"extended":[58],"reasoning.Our":[59],"experiments":[60],"show":[61],"that":[62,88,136],"using":[63],"with":[65],"ORM":[66],"achieves":[67],"score":[69],"of":[70,104],"35.8":[71],"on":[72,76,113],"while":[74,107],"BF":[75,108],"MR1-1.5Battains":[77],"35.2.Although":[78],"\"thinking":[79],"LLMs\"":[80],"have":[81],"recently":[82],"garnered":[83],"significant":[84],"attention,":[85],"find":[87],"their":[89],"performance":[90],"is":[91],"comparable":[92],"to":[93,101,144],"traditional":[94],"methods":[96,133],"like":[97],"best-of-N":[98],"once":[99],"constrained":[100],"similar":[102],"levels":[103],"inference":[105],"FLOPs.Moreover,":[106],"yields":[109],"20-point":[111],"improvement":[112],"English":[114],"AIME,":[115],"it":[116],"provides":[117],"only":[118],"1.94-point":[120],"average":[121],"gain":[122],"across":[123,128],"other":[124,130],"languages-a":[125],"pattern":[126],"consistent":[127],"studied-highlighting":[135],"may":[139],"not":[140],"generalize":[141],"as":[142],"effectively":[143],"tasks.To":[146],"foster":[147],"further":[148],"research,":[149],"release":[151],"evaluation":[155],"results.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-10-10T00:00:00"}
