{"id":"https://openalex.org/W4385565281","doi":"https://doi.org/10.18653/v1/2023.bea-1.58","title":"Beyond Black Box AI generated Plagiarism Detection: From Sentence to Document Level","display_name":"Beyond Black Box AI generated Plagiarism Detection: From Sentence to Document Level","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385565281","doi":"https://doi.org/10.18653/v1/2023.bea-1.58"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.bea-1.58","doi":"https://doi.org/10.18653/v1/2023.bea-1.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.bea-1.58","pdf_url":"https://aclanthology.org/2023.bea-1.58.pdf","source":{"id":"https://openalex.org/S4306421257","display_name":"Workshop on Innovative Use of NLP for Building Educational Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.bea-1.58.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092595484","display_name":"Ali Quidwai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Quidwai","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410485","display_name":"Chunhui Li","orcid":"https://orcid.org/0000-0003-0203-7088","observed_orcids":["https://orcid.org/0000-0003-0203-7088"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunhui Li","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110042006","display_name":"Parijat Dube","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Parijat Dube","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110042006"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":5.9984,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96326087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"727","last_page":"735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.8593999743461609,"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":0.8593999743461609,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.057999998331069946,"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/T14414","display_name":"Artificial Intelligence in Education","score":0.018799999728798866,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-generated-text-detection","display_name":"AI-generated text detection","score":0.8880000114440918},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"plagiarism detection","score":0.9369999766349792},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9449999928474426},{"id":"https://openalex.org/keywords/academic-writing","display_name":"academic writing","score":0.7820000052452087},{"id":"https://openalex.org/keywords/paraphrase-generation","display_name":"paraphrase generation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.7770000100135803},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"cosine similarity","score":0.9520000219345093},{"id":"https://openalex.org/keywords/human-vs-ai-text-classification","display_name":"human vs AI text classification","score":0.753000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105849027633667},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.6797255277633667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6591399312019348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6481406092643738},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6041202545166016},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5592905282974243},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5370897650718689},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42961233854293823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.15375849604606628},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.bea-1.58","doi":"https://doi.org/10.18653/v1/2023.bea-1.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.bea-1.58","pdf_url":"https://aclanthology.org/2023.bea-1.58.pdf","source":{"id":"https://openalex.org/S4306421257","display_name":"Workshop on Innovative Use of NLP for Building Educational Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.bea-1.58","doi":"https://doi.org/10.18653/v1/2023.bea-1.58","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.bea-1.58","pdf_url":"https://aclanthology.org/2023.bea-1.58.pdf","source":{"id":"https://openalex.org/S4306421257","display_name":"Workshop on Innovative Use of NLP for Building Educational Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6164000034332275}],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.8899999856948853}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385565281.pdf","grobid_xml":"https://content.openalex.org/works/W4385565281.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2493916176","https://openalex.org/W2611159092","https://openalex.org/W2963647337","https://openalex.org/W2969958763","https://openalex.org/W4317553041","https://openalex.org/W4318351452","https://openalex.org/W4319773014","https://openalex.org/W4324299222","https://openalex.org/W4361193535","https://openalex.org/W4367369681","https://openalex.org/W4392240262"],"related_works":["https://openalex.org/W7127054669","https://openalex.org/W4410910662","https://openalex.org/W7154725413","https://openalex.org/W7213866755","https://openalex.org/W7133536832","https://openalex.org/W4409917353","https://openalex.org/W7220018775","https://openalex.org/W7220127396","https://openalex.org/W7127050837","https://openalex.org/W7161054259"],"abstract_inverted_index":{"The":[0],"increasing":[1],"reliance":[2],"on":[3,82],"large":[4],"language":[5,35],"models":[6],"(LLMs)":[7],"in":[8,16,101,116],"academic":[9,117],"writing":[10],"has":[11],"led":[12],"to":[13,73,98],"a":[14,30,56,64,77,108,135],"rise":[15],"plagiarism.Existing":[17],"AI-generated":[18,143],"text":[19],"classifiers":[20],"have":[21],"limited":[22],"accuracy":[23,100],"and":[24,45,67,104,110,133,141],"often":[25],"produce":[26],"false":[27],"positives.We":[28],"propose":[29],"novel":[31],"approach":[32,95],"using":[33,76],"natural":[34],"processing":[36],"(NLP)":[37],"techniques,":[38],"offering":[39],"quantifiable":[40],"metrics":[41],"at":[42],"both":[43],"sentence":[44],"document":[46],"levels":[47],"for":[48,113,127],"easier":[49],"interpretation":[50],"by":[51],"human":[52,103],"evaluators.Our":[53],"method":[54,119],"employs":[55],"multi-faceted":[57],"approach,":[58],"generating":[59],"multiple":[60],"paraphrased":[61],"versions":[62],"of":[63,139],"given":[65],"question":[66],"inputting":[68],"them":[69],"into":[70],"the":[71,92,125],"LLM":[72,122],"generate":[74],"answers.By":[75],"contrastive":[78],"loss":[79],"function":[80],"based":[81],"cosine":[83],"similarity,":[84],"we":[85],"match":[86],"generated":[87],"sentences":[88],"with":[89,121],"those":[90],"from":[91],"student's":[93],"response.Our":[94],"achieves":[96],"up":[97],"94%":[99],"classifying":[102],"AI":[105],"text,":[106],"providing":[107],"robust":[109],"adaptable":[111],"solution":[112],"plagiarism":[114],"detection":[115],"settings.This":[118],"improves":[120],"advancements,":[123],"reducing":[124],"need":[126],"new":[128],"model":[129],"training":[130],"or":[131],"reconfiguration,":[132],"offers":[134],"more":[136],"transparent":[137],"way":[138],"evaluating":[140],"detecting":[142],"text.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}