{"id":"https://openalex.org/W4402817791","doi":"https://doi.org/10.1145/3695868","title":"Building a Coding Assistant via the Retrieval-Augmented Language Model","display_name":"Building a Coding Assistant via the Retrieval-Augmented Language Model","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402817791","doi":"https://doi.org/10.1145/3695868"},"language":"en","primary_location":{"id":"doi:10.1145/3695868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695868","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","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/A5064054298","display_name":"Xinze Li","orcid":"https://orcid.org/0000-0003-3014-0875"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinze Li","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0003-3014-0875","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanbin Wang","orcid":"https://orcid.org/0009-0008-0720-1610"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbin Wang","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University, China"],"raw_orcid":"https://orcid.org/0009-0008-0720-1610","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106671208","display_name":"Zhenghao Liu","orcid":"https://orcid.org/0000-0003-0083-3224"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Liu","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0003-0083-3224","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065529689","display_name":"Shi Yu","orcid":"https://orcid.org/0000-0001-6335-1076"},"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":"Shi Yu","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0001-6335-1076","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032568661","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0001-5408-3145"},"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":"Shuo Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0001-5408-3145","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034266748","display_name":"Yukun Yan","orcid":"https://orcid.org/0000-0003-2421-7098"},"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":"Yukun Yan","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-2421-7098","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084821990","display_name":"Yu-Kai Fu","orcid":"https://orcid.org/0000-0003-1094-9335"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukai Fu","raw_affiliation_strings":["Chinese Academy of Sciences, Shenyang, China","Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-1094-9335","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013145169","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0001-7422-6254"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0001-7422-6254","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0002-3171-8889","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6894,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91107236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"43","issue":"2","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.991100013256073,"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/computer-science","display_name":"Computer science","score":0.6173022389411926},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6142509579658508},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5049007534980774},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33560043573379517},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.33408963680267334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33346229791641235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32709774374961853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1111188530921936},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08086386322975159},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05495956540107727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173022389411926},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6142509579658508},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5049007534980774},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33560043573379517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.33408963680267334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33346229791641235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32709774374961853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1111188530921936},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08086386322975159},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05495956540107727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695868","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3305952834","display_name":null,"funder_award_id":"No. N2416012","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6779974588","display_name":null,"funder_award_id":"No. 92267201, No. 62206042, and No. U23B2019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2102543548","https://openalex.org/W2158439356","https://openalex.org/W2965373594","https://openalex.org/W2979826702","https://openalex.org/W2981852735","https://openalex.org/W2998702515","https://openalex.org/W3021282678","https://openalex.org/W3022049116","https://openalex.org/W3026732421","https://openalex.org/W3099700870","https://openalex.org/W3115295967","https://openalex.org/W3154898636","https://openalex.org/W4249573750","https://openalex.org/W4252076394","https://openalex.org/W4378474184","https://openalex.org/W4384345649","https://openalex.org/W4389519118","https://openalex.org/W4389519225","https://openalex.org/W4389519352","https://openalex.org/W4403942906","https://openalex.org/W6666761814","https://openalex.org/W6734897383"],"related_works":["https://openalex.org/W4213212078","https://openalex.org/W405926467","https://openalex.org/W4402742086","https://openalex.org/W1965611333","https://openalex.org/W2032228042","https://openalex.org/W1505098369","https://openalex.org/W1999916109","https://openalex.org/W3132349679","https://openalex.org/W37840851","https://openalex.org/W4251713484"],"abstract_inverted_index":{"Pretrained":[0],"language":[1,31,81,119,194,197],"models":[2,82,120],"have":[3],"shown":[4],"strong":[5],"effectiveness":[6,230],"in":[7,177,222],"code-related":[8],"tasks,":[9],"such":[10],"as":[11,115,209],"code":[12,14,16,19,39,55,62,83,90,99,106,112,124,136,145,159,179,184,201,224,233,253],"retrieval,":[13],"generation,":[15],"summarization,":[17],"and":[18,59,74,85,92,139,161,168,174,186,195,245],"completion":[20],"tasks.":[21,234],"In":[22],"this":[23],"article,":[24],"we":[25],"propose":[26],"COde":[27],"assistaNt":[28],"viA":[29],"retrieval-augmeNted":[30],"model":[32,66],"(CONAN),":[33],"which":[34,117],"aims":[35],"to":[36,79,198,227,241],"build":[37],"a":[38,54,60,97,104],"assistant":[40,211],"by":[41,163,172],"mimicking":[42],"the":[43,111,123,178,182,200,237,249],"knowledge-seeking":[44],"behaviors":[45],"of":[46,53,239],"humans":[47],"during":[48],"coding.":[49],"Specifically,":[50],"it":[51],"consists":[52],"structure-aware":[56,84],"retriever":[57],"(CONAN-R)":[58],"dual-view":[61,98],"representation-based":[63],"retrieval-augmented":[64,105],"generation":[65,107,137,146,202],"(CONAN-G).":[67],"CONAN-R":[68],"pretrains":[69],"CodeT5":[70],"using":[71],"Code-Documentation":[72],"Alignment":[73],"Masked":[75],"Entity":[76],"Prediction":[77],"tasks":[78,138],"make":[80],"learn":[86],"effective":[87],"representations":[88,156],"for":[89,102,157,212],"snippets":[91,160,185],"documentation.":[93],"Then":[94],"CONAN-G":[95,109],"designs":[96],"representation":[100],"mechanism":[101],"implementing":[103],"model.":[108],"regards":[110],"documentation":[113,162,187],"descriptions":[114],"prompts,":[116],"help":[118,246],"better":[121],"understand":[122],"semantics.":[125],"Our":[126,148],"experiments":[127],"show":[128,151],"that":[129,152],"CONAN":[130,153,204,240],"achieves":[131],"convincing":[132],"performance":[133],"on":[134,231],"different":[135],"significantly":[140],"outperforms":[141],"previous":[142],"retrieval":[143],"augmented":[144],"models.":[147],"further":[149],"analyses":[150],"learns":[154],"tailored":[155],"both":[158,192],"aligning":[164],"code-documentation":[165],"data":[166],"pairs":[167],"capturing":[169],"structural":[170],"semantics":[171],"masking":[173],"predicting":[175],"entities":[176],"data.":[180],"Additionally,":[181],"retrieved":[183,252],"provide":[188],"necessary":[189,243],"information":[190,244],"from":[191,251],"program":[193],"natural":[196],"assist":[199],"process.":[203],"can":[205],"also":[206],"be":[207],"used":[208],"an":[210],"Large":[213],"Language":[214],"Models":[215],"(LLMs),":[216],"providing":[217],"LLMs":[218],"with":[219],"external":[220],"knowledge":[221],"shorter":[223],"document":[225],"lengths":[226],"improve":[228],"their":[229],"various":[232],"It":[235],"shows":[236],"ability":[238],"extract":[242],"filter":[247],"out":[248],"noise":[250],"documents.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}