{"id":"https://openalex.org/W4412944815","doi":"https://doi.org/10.18653/v1/2025.acl-long.1158","title":"CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","display_name":"CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944815","doi":"https://doi.org/10.18653/v1/2025.acl-long.1158"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1158","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1158","pdf_url":null,"source":null,"license":null,"license_id":null,"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"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089618727","display_name":"Ruiyang Xu","orcid":"https://orcid.org/0000-0002-8521-3181"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053372458","display_name":"Jialun Cao","orcid":"https://orcid.org/0000-0003-4892-6294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialun Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103090910","display_name":"Yaojie Lu","orcid":"https://orcid.org/0000-0002-5842-7715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaojie Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003031253","display_name":"Ming Wen","orcid":"https://orcid.org/0000-0001-5588-9618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090777164","display_name":"Hongyu Lin","orcid":"https://orcid.org/0009-0001-5857-9663"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620300","display_name":"Xianpei Han","orcid":"https://orcid.org/0000-0002-1304-6302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianpei Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100969846","display_name":"Ben He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034057959","display_name":"Shing-Chi Cheung","orcid":"https://orcid.org/0000-0002-3508-7172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shing-Chi Cheung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101512153","display_name":"Le Sun","orcid":"https://orcid.org/0000-0003-2696-7140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Sun","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":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23762","last_page":"23779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6963000297546387,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.6963000297546387,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.6498000025749207,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.5907999873161316,"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/computer-science","display_name":"Computer science","score":0.7932839393615723},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7906514406204224},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6205652356147766},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5276314616203308},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39507970213890076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33131834864616394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932839393615723},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7906514406204224},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6205652356147766},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5276314616203308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39507970213890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33131834864616394},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1158","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1158","pdf_url":null,"source":null,"license":null,"license_id":null,"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:repository.hkust.edu.hk:1783.1-167059","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167059","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Code":[0],"benchmarks":[1,27,33,60,67,89],"such":[2,46,100],"as":[3,47,101],"HumanEval":[4],"are":[5,34,84],"widely":[6],"adopted":[7],"to":[8,167,185],"evaluate":[9],"Large":[10],"Language":[11],"Models'":[12],"(LLMs)":[13],"coding":[14,53,82],"capabilities.":[15],"However,":[16],"there":[17],"is":[18,56],"an":[19,80],"unignorable":[20],"programming":[21,44,124],"language":[22,169,183,199],"bias":[23,55],"in":[24,42,97,140,150,175,234],"existing":[25],"code":[26,31,63,69,118],"-":[28],"over":[29],"95%":[30],"generation":[32,64],"dominated":[35],"by":[36],"Python,":[37],"leaving":[38],"the":[39,144,196,238],"LLMs'":[40],"capabilities":[41],"other":[43,217,235],"languages":[45],"Java":[48],"and":[49,75,93,95,154,160,204],"C/C++":[50],"unknown.":[51],"Moreover,":[52],"task":[54],"also":[57],"crucial.":[58],"Most":[59],"focus":[61],"on":[62,163,226],"capability,":[65,83],"while":[66,211],"for":[68,132],"reasoning":[70,73,78,119],"(given":[71],"input,":[72],"output;":[74],"given":[76],"output,":[77],"input),":[79],"essential":[81],"insufficient.":[85],"Yet,":[86],"constructing":[87],"multi-lingual":[88,117],"can":[90,228],"be":[91],"expensive":[92],"labor-intensive,":[94],"codes":[96],"contest":[98],"websites":[99],"Leetcode":[102],"suffer":[103],"from":[104],"data":[105],"contamination":[106],"during":[107],"training.":[108],"To":[109],"fill":[110],"this":[111],"gap,":[112],"we":[113,177],"propose":[114],"CRUXEVAL-X,":[115],"a":[116,151,207,222],"benchmark":[120],"that":[121],"contains":[122],"19":[123],"languages.":[125,218],"It":[126],"comprises":[127],"at":[128,230],"least":[129],"600":[130],"subjects":[131],"each":[133],"language,":[134],"along":[135],"with":[136,216],"19K":[137],"content-consistent":[138],"tests":[139],"total.":[141],"In":[142],"particular,":[143],"construction":[145],"pipeline":[146],"of":[147,191,241],"CRUXEVAL-X":[148],"works":[149],"fully":[152],"automated":[153],"test-guided":[155],"manner,":[156],"which":[157],"iteratively":[158],"generates":[159],"repairs":[161],"based":[162],"execution":[164],"feedback.":[165],"Also,":[166],"cross":[168],"barriers":[170],"(e.g.,":[171],"dynamic/static":[172],"type":[173],"systems":[174],"Python/C++),":[176],"formulated":[178],"various":[179],"transition":[180],"rules":[181],"between":[182,198],"pairs":[184],"facilitate":[186],"translation.":[187],"Our":[188],"extensive":[189],"evaluation":[190],"24":[192],"representative":[193],"LLMs":[194],"reveals":[195],"correlation":[197,215],"pairs.":[200],"For":[201],"example,":[202],"TypeScript":[203],"JavaScript":[205],"show":[206],"significant":[208],"positive":[209],"correlation,":[210],"Racket":[212],"has":[213],"less":[214],"More":[219],"interestingly,":[220],"even":[221],"model":[223],"trained":[224],"solely":[225],"Python":[227],"achieve":[229],"most":[231],"34.4%":[232],"Pass@1":[233],"languages,":[236],"revealing":[237],"cross-language":[239],"generalization":[240],"LLMs.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}