{"id":"https://openalex.org/W4399631347","doi":"https://doi.org/10.1145/3643916.3645030","title":"Investigating the Efficacy of Large Language Models for Code Clone Detection","display_name":"Investigating the Efficacy of Large Language Models for Code Clone Detection","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4399631347","doi":"https://doi.org/10.1145/3643916.3645030"},"language":"en","primary_location":{"id":"doi:10.1145/3643916.3645030","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643916.3645030","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643916.3645030","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3643916.3645030","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029465135","display_name":"Mohamad Khajezade","orcid":"https://orcid.org/0000-0002-2433-4182"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamad Khajezade","raw_affiliation_strings":["University of British Columbia, Kelowna, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2433-4182","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051362592","display_name":"Jie JW Wu","orcid":"https://orcid.org/0000-0002-7895-2023"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jie JW Wu","raw_affiliation_strings":["University of British Columbia, Kelowna, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7895-2023","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029327446","display_name":"Fatemeh H. Fard","orcid":"https://orcid.org/0000-0002-4505-6257"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fatemeh Hendijani Fard","raw_affiliation_strings":["University of British Columbia, Kelowna, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4505-6257","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077601628","display_name":"Gema Rodr\u00edguez-P\u00e9rez","orcid":"https://orcid.org/0000-0002-0062-8418"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gema Rodriguez-Perez","raw_affiliation_strings":["University of British Columbia, Kelowna, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0062-8418","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085128370","display_name":"Mohamed Shehata","orcid":"https://orcid.org/0000-0002-8464-8650"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamed Sami Shehata","raw_affiliation_strings":["University of British Columbia, Kelowna, British Columbia, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8464-8650","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, British Columbia, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4039,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98419118,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9869999885559082,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9869999885559082,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9800000190734863,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9782999753952026,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7126559615135193},{"id":"https://openalex.org/keywords/clone","display_name":"clone (Java method)","score":0.5708559155464172},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5610234141349792},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4871968626976013},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35470151901245117},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07200348377227783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126559615135193},{"id":"https://openalex.org/C81089528","wikidata":"https://www.wikidata.org/wiki/Q5134986","display_name":"clone (Java method)","level":3,"score":0.5708559155464172},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5610234141349792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4871968626976013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35470151901245117},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07200348377227783},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3643916.3645030","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643916.3645030","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643916.3645030","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3643916.3645030","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3643916.3645030","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3643916.3645030","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1333960756","display_name":null,"funder_award_id":"05175","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G832689143","display_name":null,"funder_award_id":"RGPIN-2019","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399631347.pdf","grobid_xml":"https://content.openalex.org/works/W4399631347.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2441881010","https://openalex.org/W2547621596","https://openalex.org/W2945440850","https://openalex.org/W2965373594","https://openalex.org/W3008088841","https://openalex.org/W3086007799","https://openalex.org/W3126675481","https://openalex.org/W3165784750","https://openalex.org/W3198188208","https://openalex.org/W3209721572","https://openalex.org/W3212083716","https://openalex.org/W4210550462","https://openalex.org/W4281763794","https://openalex.org/W4308441536","https://openalex.org/W4310713606","https://openalex.org/W4312537169","https://openalex.org/W4313563720","https://openalex.org/W4384302749","https://openalex.org/W4385967654","https://openalex.org/W4386472818","https://openalex.org/W4386722158","https://openalex.org/W6732226717","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2377327490","https://openalex.org/W2560253012","https://openalex.org/W1524590520","https://openalex.org/W2412288087","https://openalex.org/W2371792548","https://openalex.org/W1697705604","https://openalex.org/W2419862115","https://openalex.org/W2017092658"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"success":[7],"in":[8,26,35,126,131,148,154],"various":[9],"natural":[10],"language":[11],"processing":[12],"and":[13,106,128,144,162,181,200],"software":[14],"engineering":[15],"tasks,":[16],"such":[17,50,76],"as":[18,51,77],"code":[19,52,124],"generation.":[20,57],"The":[21],"LLMs":[22,72,93],"are":[23,41,60],"mainly":[24],"utilized":[25],"the":[27,33,37,44,69,80,90,142,152,179,182,186,192],"prompt-based":[28,81],"zero/few-shot":[29],"paradigm":[30],"to":[31,121,140,166],"guide":[32],"model":[34],"accomplishing":[36],"task.":[38,101],"GPT-based":[39],"models":[40,169],"one":[42],"of":[43,71,92,146,160,176,185,194],"popular":[45],"ones":[46],"studied":[47],"for":[48,73,94,170],"tasks":[49,59,75],"comment":[53],"generation":[54],"or":[55],"test":[56],"These":[58],"'generative'":[61],"tasks.":[62],"However,":[63],"there":[64],"is":[65],"limited":[66],"research":[67],"on":[68,191,204],"usage":[70],"'non-generative'":[74],"classification":[78],"using":[79,119],"paradigm.":[82],"In":[83],"this":[84],"preliminary":[85],"exploratory":[86],"study,":[87],"we":[88,113,197],"investigated":[89,115],"applicability":[91],"Code":[95],"Clone":[96],"Detection":[97],"(CCD),":[98],"a":[99,104,132],"non-generative":[100],"By":[102],"building":[103],"mono-lingual":[105,171],"cross-lingual":[107],"CCD":[108,156],"dataset":[109],"derived":[110],"from":[111],"CodeNet,":[112],"first":[114],"two":[116],"different":[117],"prompts":[118],"ChatGPT":[120,147,150],"detect":[122],"Type-4":[123],"clones":[125],"Java-Java":[127],"Java-Ruby":[129],"pairs":[130],"zero-shot":[133],"setting.":[134],"We":[135],"then":[136],"conducted":[137],"an":[138,158,174,189],"analysis":[139],"understand":[141],"strengths":[143],"weaknesses":[145],"CCD.":[149],"surpasses":[151],"baselines":[153],"cross-language":[155],"attaining":[157],"F1-score":[159,175],"0.877":[161],"achieves":[163],"comparable":[164],"performance":[165,193],"fully":[167],"fine-tuned":[168],"CCD,":[172],"with":[173],"0.878.":[177],"Also,":[178],"prompt":[180],"difficulty":[183],"level":[184],"problems":[187],"has":[188],"impact":[190],"ChatGPT.":[195],"Finally,":[196],"provide":[198],"insights":[199],"future":[201],"directions":[202],"based":[203],"our":[205],"initial":[206],"analysis1.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
