{"id":"https://openalex.org/W4320458011","doi":"https://doi.org/10.1145/3543507.3583199","title":"Do Language Models Plagiarize?","display_name":"Do Language Models Plagiarize?","publication_year":2023,"publication_date":"2023-04-26","ids":{"openalex":"https://openalex.org/W4320458011","doi":"https://doi.org/10.1145/3543507.3583199"},"language":"en","primary_location":{"id":"doi:10.1145/3543507.3583199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/7634243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401542","display_name":"Jooyoung Lee","orcid":"https://orcid.org/0000-0002-4635-247X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jooyoung Lee","raw_affiliation_strings":["Penn State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-4635-247X","affiliations":[{"raw_affiliation_string":"Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039440984","display_name":"Thai Le","orcid":"https://orcid.org/0000-0001-9632-6870"},"institutions":[{"id":"https://openalex.org/I368840534","display_name":"University of Mississippi","ror":"https://ror.org/02teq1165","country_code":"US","type":"education","lineage":["https://openalex.org/I368840534","https://openalex.org/I4210141039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thai Le","raw_affiliation_strings":["University of Mississippi, USA"],"raw_orcid":"https://orcid.org/0000-0001-9632-6870","affiliations":[{"raw_affiliation_string":"University of Mississippi, USA","institution_ids":["https://openalex.org/I368840534"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006335513","display_name":"Jinghui Chen","orcid":"https://orcid.org/0000-0002-1486-4526"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghui Chen","raw_affiliation_strings":["Penn State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-1486-4526","affiliations":[{"raw_affiliation_string":"Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["Penn State University, USA"],"raw_orcid":"https://orcid.org/0000-0001-8371-7629","affiliations":[{"raw_affiliation_string":"Penn State University, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3637","last_page":"3647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9986000061035156,"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":0.9986000061035156,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6194741725921631},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3696843385696411},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3384626805782318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6194741725921631},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3696843385696411},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3384626805782318}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543507.3583199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543507.3583199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:7634243","is_oa":true,"landing_page_url":"https://zenodo.org/record/7634243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:7634243","is_oa":true,"landing_page_url":"https://zenodo.org/record/7634243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5199999809265137,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1790180460","https://openalex.org/W1966924370","https://openalex.org/W2006407062","https://openalex.org/W2098862431","https://openalex.org/W2115269749","https://openalex.org/W2147528976","https://openalex.org/W2396655261","https://openalex.org/W2469132828","https://openalex.org/W2566373727","https://openalex.org/W2582715692","https://openalex.org/W2773143256","https://openalex.org/W2998431971","https://openalex.org/W3020013471","https://openalex.org/W3027379683","https://openalex.org/W3058517477","https://openalex.org/W3096214574","https://openalex.org/W3101891351","https://openalex.org/W3112689365","https://openalex.org/W3208416306","https://openalex.org/W4205507439","https://openalex.org/W4229623782"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Past":[0],"literature":[1],"has":[2,171],"illustrated":[3],"that":[4,42,95,140],"language":[5,19],"models":[6,37,197],"(LMs)":[7],"often":[8],"memorize":[9],"parts":[10],"of":[11,57,80,99,113,121,143,158,184,220],"training":[12,33,47,72,145,166,188,200],"instances":[13],"and":[14,62,74,110,125,137,161,186,209,227,236],"reproduce":[15],"them":[16],"in":[17,68,90,103,223],"natural":[18],"generation":[20],"(NLG)":[21],"processes.":[22],"However,":[23],"it":[24],"is":[25,147],"unclear":[26],"to":[27,46,70,178],"what":[28],"extent":[29],"LMs":[30,82,104,114,185,222],"\u201creuse\u201d":[31],"a":[32,141],"corpus.":[34],"For":[35],"instance,":[36],"can":[38,204],"generate":[39],"paraphrased":[40],"sentences":[41],"are":[43,87,115,176,239],"contextually":[44],"similar":[45],"samples.":[48],"In":[49],"this":[50],"work,":[51],"therefore,":[52],"we":[53],"study":[54],"three":[55,97],"types":[56,98],"plagiarism":[58,78,100,122,129],"(i.e.,":[59],"verbatim,":[60],"paraphrase,":[61],"idea)":[63],"among":[64],"GPT-2":[65],"generated":[66,169],"texts,":[67],"comparison":[69],"its":[71],"data,":[73],"further":[75],"analyze":[76],"the":[77,119,150,182,218,232],"patterns":[79,130,175],"fine-tuned":[81,127],"with":[83,118,198],"domain-specific":[84],"corpora":[85],"which":[86],"extensively":[88],"used":[89],"practice.":[91],"Our":[92],"results":[93],"suggest":[94],"(1)":[96],"widely":[101],"exist":[102],"beyond":[105],"memorization,":[106],"(2)":[107],"both":[108,181],"size":[109,183],"decoding":[111],"methods":[112],"strongly":[116],"associated":[117],"degrees":[120],"they":[123],"exhibit,":[124],"(3)":[126],"LMs\u2019":[128,144],"vary":[131],"based":[132],"on":[133,217],"their":[134,156,187],"corpus":[135],"similarity":[136],"homogeneity.":[138],"Given":[139],"majority":[142],"data":[146,189],"scraped":[148],"from":[149,165],"Web":[151],"without":[152],"informing":[153],"content":[154,203],"owners,":[155],"reiteration":[157],"words,":[159],"phrases,":[160],"even":[162],"core":[163],"ideas":[164],"sets":[167],"into":[168],"texts":[170],"ethical":[172],"implications.":[173],"Their":[174],"likely":[177],"exacerbate":[179],"as":[180],"increase,":[190],"raising":[191],"concerns":[192],"about":[193],"indiscriminately":[194],"pursuing":[195],"larger":[196,199],"corpora.":[201],"Plagiarized":[202],"also":[205],"contain":[206],"individuals\u2019":[207],"personal":[208],"sensitive":[210],"information.":[211],"These":[212],"findings":[213],"overall":[214],"cast":[215],"doubt":[216],"practicality":[219],"current":[221],"mission-critical":[224],"writing":[225],"tasks":[226],"urge":[228],"more":[229],"discussions":[230],"around":[231],"observed":[233],"phenomena.":[234],"Data":[235],"source":[237],"code":[238],"available":[240],"at":[241],"https://github.com/Brit7777/LM-plagiarism.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}