{"id":"https://openalex.org/W7138029243","doi":"https://doi.org/10.1609/aaai.v40i38.40471","title":"Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning","display_name":"Towards Better Code Understanding in Decoder-Only Models with Contrastive Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138029243","doi":"https://doi.org/10.1609/aaai.v40i38.40471"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i38.40471","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40471","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i38.40471","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiayi Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Lin","raw_affiliation_strings":["International Digital Economy Academy\nTencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy\nTencent","institution_ids":["https://openalex.org/I4210110242"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanlin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanlin Wang","raw_affiliation_strings":["Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yibiao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibiao Yang","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["International Digital Economy Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Yutao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutao Xie","raw_affiliation_strings":["International Digital Economy Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32006","last_page":"32014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9829999804496765,"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":0.9829999804496765,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.0017999999690800905,"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/discriminative-model","display_name":"Discriminative model","score":0.7128999829292297},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6862999796867371},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6065000295639038},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5722000002861023},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.4810999929904938},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44530001282691956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187999725341797},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7128999829292297},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6862999796867371},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5722000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.4810999929904938},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.29330000281333923},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2858999967575073},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i38.40471","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40471","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40471","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40471","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7072151899337769}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,20],"large-scale":[3],"code":[4,27,45,50,71,98,102,120,161,165,181,190,207],"generation":[5,99,208],"models":[6,17,39,66,100,200],"have":[7],"led":[8],"to":[9,57,101,114,133,156],"remarkable":[10],"progress":[11],"producing":[13],"high-quality":[14],"code.":[15],"These":[16,192],"are":[18],"trained":[19],"a":[21,30,88,128,202],"self-supervised":[22],"manner":[23],"on":[24,44,69,143,159],"extensive":[25],"unlabeled":[26],"corpora":[28],"using":[29],"decoder-only":[31,38,97,108,139,199],"architecture.":[32],"However,":[33],"despite":[34],"their":[35,58],"generative":[36],"strength,":[37],"often":[40],"exhibit":[41],"limited":[42],"performance":[43,154],"understanding":[46,75,103,162],"tasks":[47],"such":[48],"as":[49,201],"search":[51,166],"and":[52,81,117,167,209],"clone":[53,168],"detection,":[54],"primarily":[55],"due":[56],"generation-oriented":[59],"training":[60,63],"objectives.":[61],"While":[62],"large":[64],"encoder-only":[65],"from":[67,95],"scratch":[68],"massive":[70],"datasets":[72,146],"can":[73,110],"improve":[74],"ability":[76],"but":[77],"remains":[78],"computationally":[79],"expensive":[80],"time-consuming.":[82],"In":[83],"this":[84,123],"paper,":[85],"we":[86,125],"explore":[87],"more":[89],"efficient":[90],"alternative":[91],"by":[92,183],"transferring":[93],"knowledge":[94],"pre-trained":[96],"tasks.":[104],"We":[105],"investigate":[106],"how":[107],"architectures":[109],"be":[111],"effectively":[112],"adapted":[113],"learn":[115],"discriminative":[116],"semantically":[118,188],"meaningful":[119],"representations.":[121],"To":[122],"end,":[124],"propose":[126],"CL4D,":[127],"contrastive":[129],"learning":[130],"framework":[131],"tailored":[132],"strengthen":[134],"the":[135,177,185,195],"representation":[136],"capabilities":[137],"of":[138,180,197],"models.":[140],"Extensive":[141],"experiments":[142],"multiple":[144],"benchmark":[145],"demonstrate":[147],"that":[148,173],"CL4D":[149,174],"achieves":[150],"competitive":[151],"or":[152],"superior":[153],"compared":[155],"existing":[157],"methods":[158],"representative":[160],"tasks,":[163],"including":[164],"detection.":[169],"Further":[170],"analysis":[171],"reveals":[172],"substantially":[175],"improves":[176],"semantic":[178],"alignment":[179],"representations":[182],"reducing":[184],"distance":[186],"between":[187],"similar":[189],"snippets.":[191],"findings":[193],"highlight":[194],"feasibility":[196],"leveraging":[198],"unified":[203],"backbone":[204],"for":[205],"both":[206],"understanding.":[210]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-14T00:00:00"}