{"id":"https://openalex.org/W4406892725","doi":"https://doi.org/10.1109/fllm63129.2024.10852497","title":"Can Large Language Model Detect Plagiarism in Source Code?","display_name":"Can Large Language Model Detect Plagiarism in Source Code?","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406892725","doi":"https://doi.org/10.1109/fllm63129.2024.10852497"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-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/A5116057110","display_name":"William Brach","orcid":null},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"William Brach","raw_affiliation_strings":["Slovak University of Technology,Faculty of Informatics and Information Technologies,Bratislava,Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Slovak University of Technology,Faculty of Informatics and Information Technologies,Bratislava,Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087743833","display_name":"Kristi\u00e1n Ko\u0161\u0165\u00e1l","orcid":"https://orcid.org/0000-0003-0679-4588"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Kristi\u00e1n Ko\u0161t\u2019\u00e1l","raw_affiliation_strings":["Slovak University of Technology,Faculty of Informatics and Information Technologies,Bratislava,Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Slovak University of Technology,Faculty of Informatics and Information Technologies,Bratislava,Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088100575","display_name":"Michal Ries","orcid":"https://orcid.org/0000-0002-9233-7123"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Michal Ries","raw_affiliation_strings":["Slovak University of Technology,Faculty of Informatics and Information Technologies,Bratislava,Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Slovak University of Technology,Faculty of Informatics and Information Technologies,Bratislava,Slovakia","institution_ids":["https://openalex.org/I110757952"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5116057110"],"corresponding_institution_ids":["https://openalex.org/I110757952"],"apc_list":null,"apc_paid":null,"fwci":0.492,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76002335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"370","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9194999933242798,"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/T13629","display_name":"Text Readability and Simplification","score":0.9031999707221985,"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":0.7785776257514954},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5590020418167114},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5045567750930786},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.5036386847496033},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4341953694820404},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3536481261253357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785776257514954},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5590020418167114},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5045567750930786},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.5036386847496033},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4341953694820404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3536481261253357},{"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:10.1109/fllm63129.2024.10852497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3002459461","https://openalex.org/W3173165160","https://openalex.org/W3127649977","https://openalex.org/W4287331153","https://openalex.org/W2155491649","https://openalex.org/W4224015079","https://openalex.org/W1985086575","https://openalex.org/W2100097978","https://openalex.org/W4300711971","https://openalex.org/W2914826750"],"abstract_inverted_index":{"The":[0,30,61],"issue":[1],"of":[2,18,27,32,56,58,63,80,83,96,124,139,173],"code":[3,28,59,142,177],"plagiarism":[4,125,191],"represents":[5],"a":[6,54],"significant":[7],"challenge":[8],"in":[9,23,45,77,141,175,194],"the":[10,16,25,78,87,116,120,127,136,160,171,183],"academic":[11,180],"environment.":[12],"This":[13,165],"study":[14,65,166],"examines":[15],"potential":[17,138],"large":[19],"language":[20],"models":[21],"(LLMs)":[22],"improving":[24],"detection":[26,79,192],"plagiarism.":[29,60,84],"performance":[31],"several":[33],"LLMs,":[34],"including":[35],"GPT-4o,":[36],"GPT-3.5":[37],"Turbo,":[38],"LLaMA":[39,108],"3,":[40],"and":[41,92,179,189,198,205],"CodeLlama,":[42],"is":[43,99,146],"evaluated":[44],"comparison":[46],"to":[47,72,101,118],"conventional":[48],"tools,":[49],"such":[50,106],"as":[51,107,130],"JPlag,":[52],"across":[53],"range":[55],"levels":[57],"findings":[62],"our":[64,212],"illustrate":[66],"that":[67,103,149],"state-of-the-art":[68],"LLMs":[69,140],"are":[70],"able":[71],"outperform":[73],"traditional":[74],"methods,":[75],"particularly":[76],"sophisticated":[81],"forms":[82,123],"GPT-4o":[85],"exhibited":[86],"highest":[88],"overall":[89],"accuracy":[90,129],"(78.70%)":[91],"an":[93,156],"F1":[94,112],"score":[95,113],"86.97%.":[97],"It":[98],"important":[100],"note":[102],"open-source":[104],"models,":[105],"3":[109],"(accuracy":[110],"71.53%,":[111],"82.75%),":[114],"demonstrated":[115],"ability":[117],"detect":[119],"most":[121],"complex":[122],"with":[126],"same":[128],"GPT-4o.":[131],"While":[132],"these":[133],"results":[134],"demonstrate":[135],"promising":[137],"similarity":[143],"analysis,":[144],"it":[145],"also":[147],"evident":[148],"higher":[150],"false":[151],"positive":[152],"rates":[153],"may":[154],"be":[155],"inherent":[157],"limitation,":[158],"emphasizing":[159],"need":[161],"for":[162,185],"human":[163],"oversight.":[164],"contributes":[167],"valuable":[168],"insights":[169],"into":[170],"application":[172],"AI":[174],"maintaining":[176],"integrity":[178],"honesty,":[181],"paving":[182],"way":[184],"more":[186],"effective,":[187],"interpretable,":[188],"fair":[190],"systems":[193],"software":[195],"development":[196],"education":[197],"practice.":[199],"For":[200],"further":[201],"information,":[202],"source":[203],"code,":[204],"updates":[206],"on":[207],"this":[208],"project,":[209],"please":[210],"visit":[211],"GitHub":[213],"at":[214],"https://github.com/fiit-ba/llm-plagiarism-check.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}
