{"id":"https://openalex.org/W4385562549","doi":"https://doi.org/10.1145/3580305.3599790","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","display_name":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385562549","doi":"https://doi.org/10.1145/3580305.3599790"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599790","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599790","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599790","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599790","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065248294","display_name":"Qinkai Zheng","orcid":"https://orcid.org/0000-0002-5391-9446"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinkai Zheng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102716132","display_name":"Xiao Xia","orcid":"https://orcid.org/0009-0005-9482-8769"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Xia","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102972973","display_name":"Xu Zou","orcid":"https://orcid.org/0000-0002-9471-1481"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052284218","display_name":"Yuxiao Dong","orcid":"https://orcid.org/0000-0002-6092-2002"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Dong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103032695","display_name":"Shan Wang","orcid":"https://orcid.org/0009-0005-0887-6861"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003137246","display_name":"Yufei Xue","orcid":"https://orcid.org/0009-0009-7959-0667"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Xue","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586835","display_name":"Lei Shen","orcid":"https://orcid.org/0000-0002-9786-2605"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Shen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103202206","display_name":"Zihan Wang","orcid":"https://orcid.org/0009-0007-1540-6213"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064035318","display_name":"Andi Wang","orcid":"https://orcid.org/0009-0009-2673-9990"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andi Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021656","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-2485-3951"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Zhipu.AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Zhipu.AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812366","display_name":"Teng Su","orcid":"https://orcid.org/0009-0005-9517-2845"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Su","raw_affiliation_strings":["Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639237","display_name":"Z. Yang","orcid":"https://orcid.org/0009-0008-0681-9603"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilin Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044791875","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0003-3487-4593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5065248294"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":95.1763,"has_fulltext":true,"cited_by_count":208,"citation_normalized_percentile":{"value":0.99981409,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5673","last_page":"5684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9952999949455261,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9952999949455261,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9598000049591064,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.949999988079071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8437091112136841},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8128098249435425},{"id":"https://openalex.org/keywords/javascript","display_name":"JavaScript","score":0.7170780301094055},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.7124696373939514},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6690327525138855},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5111940503120422},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4440465271472931},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4238247871398926},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.4113045930862427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3449501097202301},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3210081458091736},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2197859287261963},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.21273407340049744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8437091112136841},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8128098249435425},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.7170780301094055},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.7124696373939514},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6690327525138855},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5111940503120422},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4440465271472931},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4238247871398926},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.4113045930862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3449501097202301},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3210081458091736},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2197859287261963},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.21273407340049744},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"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":1,"locations":[{"id":"doi:10.1145/3580305.3599790","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599790","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599790","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599790","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599790","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599790","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 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1040948671","display_name":null,"funder_award_id":"61836013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3297568266","display_name":null,"funder_award_id":"6183601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5614798656","display_name":null,"funder_award_id":"61825602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6048029205","display_name":null,"funder_award_id":"62276148","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6449033798","display_name":null,"funder_award_id":"NSFC No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385562549.pdf","grobid_xml":"https://content.openalex.org/works/W4385562549.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2060610732","https://openalex.org/W2076242896","https://openalex.org/W2194775991","https://openalex.org/W2276356546","https://openalex.org/W2595233870","https://openalex.org/W2612690371","https://openalex.org/W2979826702","https://openalex.org/W2997847174","https://openalex.org/W3108032709","https://openalex.org/W3129831491","https://openalex.org/W4281669078","https://openalex.org/W4281763794","https://openalex.org/W4285225959"],"related_works":["https://openalex.org/W3007497615","https://openalex.org/W2998205945","https://openalex.org/W4389438938","https://openalex.org/W4282813445","https://openalex.org/W3128187337","https://openalex.org/W4200321676","https://openalex.org/W4317042421","https://openalex.org/W2053262616","https://openalex.org/W2104132242","https://openalex.org/W3195022246"],"abstract_inverted_index":{"Large":[0],"pre-trained":[1,39],"code":[2,35,60,70],"generation":[3,71],"models,":[4],"such":[5],"as":[6,48],"OpenAI":[7],"Codex,":[8],"can":[9,133],"generate":[10],"syntax-and":[11],"function-correct":[12],"code,":[13,155],"making":[14],"the":[15,67,83,92],"coding":[16,137],"of":[17,44,49,62,69,120,122,141],"programmers":[18],"more":[19],"productive.":[20],"In":[21,100],"this":[22],"paper,":[23],"we":[24,81,102,152],"introduce":[25],"CodeGeeX,":[26],"a":[27],"multilingual":[28,59,88],"model":[29,156],"with":[30],"13":[31],"billion":[32,42,116],"parameters":[33],"for":[34,65,86,118,139],"generation.":[36],"CodeGeeX":[37,57,132,145],"is":[38,146],"on":[40,74,106],"850":[41],"tokens":[43,117],"23":[45],"programming":[46],"languages":[47],"June":[50],"2022.":[51],"Our":[52,127],"extensive":[53],"experiments":[54],"suggest":[55],"that":[56,131],"outperforms":[58],"models":[61,89],"similar":[63],"scale":[64],"both":[66],"tasks":[68],"and":[72,98,111,160],"translation":[73],"HumanEval-X.":[75],"Building":[76],"upon":[77],"HumanEval":[78],"(Python":[79],"only),":[80],"develop":[82],"HumanEval-X":[84,161],"benchmark":[85],"evaluating":[87],"by":[90],"hand-writing":[91],"solutions":[93],"in":[94],"C++,":[95],"Java,":[96],"JavaScript,":[97],"Go.":[99],"addition,":[101],"build":[103],"CodeGeeX-based":[104],"extensions":[105],"Visual":[107],"Studio":[108],"Code,":[109],"JetBrains,":[110],"Cloud":[112],"Studio,":[113],"generating":[114],"8":[115],"tens":[119],"thousands":[121],"active":[123],"users":[124],"per":[125],"week.":[126],"user":[128],"study":[129],"demonstrates":[130],"help":[134],"to":[135],"increase":[136],"efficiency":[138],"83.4%":[140],"its":[142,154],"users.":[143],"Finally,":[144],"publicly":[147],"accessible":[148],"since":[149],"Sep.":[150],"2022,":[151],"open-sourced":[153],"weights,":[157],"API,":[158],"extensions,":[159],"at":[162],"https://github.com/THUDM/CodeGeeX.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":127},{"year":2024,"cited_by_count":60},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}