{"id":"https://openalex.org/W7166840367","doi":"https://doi.org/10.18653/v1/2026.mellm-1.16","title":"mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?","display_name":"mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166840367","doi":"https://doi.org/10.18653/v1/2026.mellm-1.16"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.mellm-1.16","doi":"https://doi.org/10.18653/v1/2026.mellm-1.16","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.mellm-1.16","pdf_url":"https://aclanthology.org/2026.mellm-1.16.pdf","source":{"id":"https://openalex.org/S7407114466","display_name":"Workshop on Multilinguality in the Era of Large Language Models (MeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.mellm-1.16.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068380743","display_name":"Yerzhan Sapenov","orcid":"https://orcid.org/0000-0001-8996-222X","observed_orcids":["https://orcid.org/0000-0001-8996-222X"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yerzhan Sapenov","raw_affiliation_strings":["School of Computer Science , Carnegie Mellon University , Pittsburgh , PA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Carnegie Mellon University , Pittsburgh , PA , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122937642","display_name":"Jaromir Savelka","orcid":"https://orcid.org/0000-0002-3674-5456","observed_orcids":["https://orcid.org/0000-0002-3674-5456"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaromir Savelka","raw_affiliation_strings":["School of Computer Science , Carnegie Mellon University , Pittsburgh , PA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Carnegie Mellon University , Pittsburgh , PA , USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4598539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6718999743461609,"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":0.6718999743461609,"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":0.29829999804496765,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01080000028014183,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/multilingual-reasoning","display_name":"multilingual reasoning","score":0.8539999723434448},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8209999799728394},{"id":"https://openalex.org/keywords/pisa","display_name":"PISA","score":0.8529999852180481},{"id":"https://openalex.org/keywords/multilingual-benchmark","display_name":"multilingual benchmark","score":0.6610000133514404},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.9359999895095825},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.5630000233650208},{"id":"https://openalex.org/keywords/inference-cost","display_name":"inference cost","score":0.6370000243186951},{"id":"https://openalex.org/keywords/token-usage","display_name":"token usage","score":0.9459999799728394},{"id":"https://openalex.org/keywords/cross-lingual-evaluation","display_name":"cross-lingual evaluation","score":0.699999988079071},{"id":"https://openalex.org/keywords/multiple-choice-questions","display_name":"multiple-choice questions","score":0.6919999718666077}],"concepts":[{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.42170000076293945},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.34619998931884766},{"id":"https://openalex.org/C47768531","wikidata":"https://www.wikidata.org/wiki/Q1127188","display_name":"Development economics","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.26019999384880066},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.24609999358654022},{"id":"https://openalex.org/C27548731","wikidata":"https://www.wikidata.org/wiki/Q88272","display_name":"Investment (military)","level":3,"score":0.23559999465942383}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.mellm-1.16","doi":"https://doi.org/10.18653/v1/2026.mellm-1.16","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.mellm-1.16","pdf_url":"https://aclanthology.org/2026.mellm-1.16.pdf","source":{"id":"https://openalex.org/S7407114466","display_name":"Workshop on Multilinguality in the Era of Large Language Models (MeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.mellm-1.16","doi":"https://doi.org/10.18653/v1/2026.mellm-1.16","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.mellm-1.16","pdf_url":"https://aclanthology.org/2026.mellm-1.16.pdf","source":{"id":"https://openalex.org/S7407114466","display_name":"Workshop on Multilinguality in the Era of Large Language Models (MeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.5740001797676086}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307894","display_name":"Accenture","ror":"https://ror.org/013g16z83"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166840367.pdf","grobid_xml":"https://content.openalex.org/works/W7166840367.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417521208","https://openalex.org/W4414880340","https://openalex.org/W7128721629","https://openalex.org/W7102695690","https://openalex.org/W7117773661","https://openalex.org/W4407759838","https://openalex.org/W7102402884","https://openalex.org/W4416039600","https://openalex.org/W4303648904","https://openalex.org/W4402669965"],"abstract_inverted_index":{"We":[0],"introduce":[1],"mmPISA-bench,":[2],"a":[3],"compact":[4],"highquality":[5],"multilingual":[6,131],"reasoning":[7,27,62,132],"benchmark":[8,19],"derived":[9],"from":[10],"the":[11,75],"OECD":[12],"Programme":[13],"for":[14,129],"International":[15],"Student":[16],"Assessment":[17],"(PISA).The":[18],"consists":[20],"of":[21,70],"25":[22],"multiple-choice":[23],"questions":[24,76,107],"that":[25,80,105,119,150],"require":[26],"in":[28,37,53,68,153],"order":[29],"to":[30,41,73,93,113],"be":[31,127],"answered":[32],"correctly.Each":[33],"question":[34],"is":[35,156],"provided":[36],"official":[38,114,135],"human":[39,94,115],"translations":[40,116,136],"43":[42],"languages":[43,155],"and":[44,65,144,148,160],"complemented":[45],"with":[46,96],"machine-translated":[47],"counterparts":[48],"(i.e.,":[49],"2,150":[50],"data":[51],"points":[52],"total).We":[54],"evaluate":[55],"two":[56],"mainstream":[57],"proprietary":[58],"LLMs":[59,82,151],"across":[60,86,100],"languages,":[61,89],"effort":[63],"levels,":[64],"translation":[66,122],"types":[67],"terms":[69],"their":[71],"ability":[72],"answer":[74],"correctly.Our":[77],"results":[78],"show":[79],"modern":[81],"can":[83],"reason":[84],"effectively":[85],"all":[87],"evaluated":[88],"achieve":[90],"accuracy":[91,111],"comparable":[92],"test-takers,":[95],"some":[97,154],"performance":[98],"variations":[99],"covered":[101],"languages.We":[102],"further":[103],"find":[104,149],"machinetranslated":[106],"do":[108],"not":[109,138],"degrade":[110],"relative":[112],"which":[117],"suggests":[118],"high-quality":[120],"machine":[121],"(synthetic":[123],"data)":[124],"might":[125],"often":[126],"adequate":[128],"large-scale":[130],"evaluations":[133],"where":[134],"are":[137],"available.Finally,":[139],"we":[140],"analyze":[141],"token":[142],"usage":[143,152],"related":[145],"inference":[146],"cost":[147],"simultaneously":[157],"more":[158],"expensive":[159],"less":[161],"accurate.":[162]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}