{"id":"https://openalex.org/W4408652593","doi":"https://doi.org/10.1145/3725213","title":"Wenwang: Toward Effectively Generating Code Beyond Standalone Functions via Generative Pre-trained Models","display_name":"Wenwang: Toward Effectively Generating Code Beyond Standalone Functions via Generative Pre-trained Models","publication_year":2025,"publication_date":"2025-03-20","ids":{"openalex":"https://openalex.org/W4408652593","doi":"https://doi.org/10.1145/3725213"},"language":"en","primary_location":{"id":"doi:10.1145/3725213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725213","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","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/A5027133048","display_name":"Hao Yu","orcid":"https://orcid.org/0000-0002-3828-7612"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-3828-7612","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791082","display_name":"Bo Shen","orcid":"https://orcid.org/0000-0002-0825-8001"},"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":"Bo Shen","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-0825-8001","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052098433","display_name":"J. Y. Zhang","orcid":"https://orcid.org/0009-0004-6438-360X"},"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":"Jiaxin Zhang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, China"],"raw_orcid":"https://orcid.org/0009-0004-6438-360X","affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079745336","display_name":"Shaoxin Lin","orcid":null},"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":"Shaoxin Lin","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0009-0000-0310-855X","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Li","orcid":"https://orcid.org/0009-0002-1572-6640"},"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":"Lin Li","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0009-0002-1572-6640","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038623189","display_name":"Guangtai Liang","orcid":"https://orcid.org/0009-0004-2454-1706"},"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":"Guangtai Liang","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0009-0004-2454-1706","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414277","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-6278-2357"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["National Research Center of Software Engineering, Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-6278-2357","affiliations":[{"raw_affiliation_string":"National Research Center of Software Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012567911","display_name":"Qianxiang Wang","orcid":"https://orcid.org/0000-0002-6598-0041"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxiang Wang","raw_affiliation_strings":["National Research Center of Software Engineering, Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-6598-0041","affiliations":[{"raw_affiliation_string":"National Research Center of Software Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048118068","display_name":"Tao Xie","orcid":"https://orcid.org/0000-0002-6731-216X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Xie","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE; SCS; Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-6731-216X","affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS; Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.827423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.972100019454956,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.968999981880188,"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":0.853313684463501},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6687873005867004},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5733562707901001},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4416294991970062},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39569753408432007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3703630566596985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853313684463501},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6687873005867004},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5733562707901001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4416294991970062},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39569753408432007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3703630566596985},{"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:10.1145/3725213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3725213","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2799054028","https://openalex.org/W2980708516","https://openalex.org/W3118781290","https://openalex.org/W3121707215","https://openalex.org/W3133702157","https://openalex.org/W3212496002","https://openalex.org/W4210252123","https://openalex.org/W4221166942","https://openalex.org/W4226463316","https://openalex.org/W4283526519","https://openalex.org/W4292779060","https://openalex.org/W4321610465","https://openalex.org/W4323037544","https://openalex.org/W4385562549","https://openalex.org/W4388483837","https://openalex.org/W4388874804","https://openalex.org/W4391558462","https://openalex.org/W6600538214","https://openalex.org/W6601899773","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W3211753092","https://openalex.org/W2386000789"],"abstract_inverted_index":{"Code":[0],"generation":[1],"models":[2,23,217],"based":[3,268],"on":[4,33,130,182,190,239,253,261,269],"the":[5,48,124,163,199,223],"pre-training":[6],"and":[7,17,28,83,86,146,165,211,231],"fine-tuning":[8,142,155,188,195],"paradigm":[9],"have":[10],"been":[11],"increasingly":[12],"attempted":[13],"by":[14,111,187],"both":[15],"academia":[16],"industry,":[18],"resulting":[19],"in":[20,114],"well-known":[21],"industrial":[22],"such":[24],"as":[25],"Codex,":[26],"CodeGen,":[27,229],"PanGu-Coder.":[29],"After":[30],"being":[31,62],"pre-trained":[32,128,271],"a":[34,39,70,74,87,91,127,141,147,169,262],"large-scale":[35],"corpus":[36],"of":[37,126,138,225,264],"code,":[38],"model":[40,129,149,244],"is":[41],"further":[42],"fine-tuned":[43,148],"with":[44,153,192,218,242],"datasets":[45],"specifically":[46],"for":[47,168],"target":[49,60],"downstream":[50],"task,":[51],"e.g.,":[52],"generating":[53,131],"code":[54,61,105,132,166,207],"from":[55],"natural":[56],"language":[57],"description.":[58],"The":[59],"generated":[63],"can":[64,202,247],"be":[65,203],"classified":[66],"into":[67],"two":[68,139],"types:":[69],"standalone":[71,134],"function,":[72,89,170],"i.e.,":[73,90],"function":[75,92],"that":[76,93,198],"invokes":[77,94],"or":[78,95,99],"accesses":[79,96],"only":[80],"built-in":[81],"functions":[82,98,108],"standard":[84],"libraries,":[85],"non-standalone":[88,107,160],"user-defined":[97],"third-party":[100],"libraries.":[101],"To":[102],"effectively":[103],"generate":[104],"especially":[106],"(largely":[109],"ignored":[110],"existing":[112,154,270],"work),":[113],"this":[115],"article,":[116],"we":[117,184],"present":[118],"Wenwang,":[119],"an":[120],"approach":[121],"to":[122,251],"improving":[123],"capability":[125],"beyond":[133],"functions.":[135,161],"Wenwang":[136],"consists":[137],"components:":[140],"dataset":[143],"named":[144,150],"WenwangData":[145,157,171,191],"WenwangCoder.":[151],"Compared":[152],"datasets,":[156],"additionally":[158],"covers":[159],"Besides":[162],"docstring":[164],"snippet":[167],"also":[172,258],"includes":[173],"its":[174],"contextual":[175,200],"information":[176,201],"collected":[177],"via":[178],"program":[179],"analysis.":[180],"Based":[181],"PanGu-Coder,":[183,230],"produce":[185],"WenwangCoder":[186,213,234,241],"PanGu-Coder":[189],"our":[193],"context-aware":[194],"technique":[196],"so":[197],"fully":[204],"leveraged":[205],"during":[206],"generation.":[208],"On":[209],"CoderEval":[210],"HumanEval,":[212,240],"outperforms":[214],"three":[215],"state-of-the-art":[216],"similar":[219,249],"parameter":[220,245],"sizes":[221,246],"(at":[222],"scale":[224],"around":[226],"300M),":[227],"namely":[228],"PanGu-FT.":[232],"Although":[233],"does":[235],"not":[236],"outperform":[237],"ChatGPT":[238,252],"smaller":[243],"achieve":[248],"effects":[250],"CoderEval.":[254],"Our":[255],"experimental":[256],"results":[257],"shed":[259],"light":[260],"number":[263],"promising":[265],"optimization":[266],"directions":[267],"models.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
