{"id":"https://openalex.org/W7119474229","doi":"https://doi.org/10.48550/arxiv.2601.03812","title":"AI Generated Text Detection","display_name":"AI Generated Text Detection","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7119474229","doi":"https://doi.org/10.48550/arxiv.2601.03812"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.03812","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.03812","pdf_url":"https://arxiv.org/pdf/2601.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.03812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122364293","display_name":"Adilkhan Alikhanov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Alikhanov, Adilkhan","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092934164","display_name":"Aidar Amangeldi","orcid":"https://orcid.org/0009-0009-5198-4680","observed_orcids":["https://orcid.org/0009-0009-5198-4680"]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Amangeldi, Aidar","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122346969","display_name":"Diar Demeubay","orcid":"https://orcid.org/0009-0006-7885-2678","observed_orcids":["https://orcid.org/0009-0006-7885-2678"]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Demeubay, Diar","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122371691","display_name":"Dilnaz Akhmetzhan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Akhmetzhan, Dilnaz","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122342157","display_name":"Nurbek Moldakhmetov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Moldakhmetov, Nurbek","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122365487","display_name":"Omar Polat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Polat, Omar","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122383048","display_name":"Galymzhan Zharas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60559429","display_name":"Nazarbayev University","ror":"https://ror.org/052bx8q98","country_code":"KZ","type":"education","lineage":["https://openalex.org/I60559429"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zharas, Galymzhan","raw_affiliation_strings":["Department of Computer Science Nazarbayev University Astana , Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Nazarbayev University Astana , Kazakhstan","institution_ids":["https://openalex.org/I60559429"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60559429"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.7387999892234802,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.7387999892234802,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.07890000194311142,"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":0.05260000005364418,"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/ai-generated-text-detection","display_name":"AI-generated text detection","score":0.9959999918937683},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8450000286102295},{"id":"https://openalex.org/keywords/academic-integrity","display_name":"academic integrity","score":0.9739999771118164},{"id":"https://openalex.org/keywords/student-plagiarism","display_name":"student plagiarism","score":0.5740000009536743},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.3630000054836273},{"id":"https://openalex.org/keywords/information-leakage","display_name":"information leakage","score":0.8309999704360962},{"id":"https://openalex.org/keywords/distilbert","display_name":"DistilBERT","score":0.781000018119812},{"id":"https://openalex.org/keywords/bilstm","display_name":"BiLSTM","score":0.9829999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7461000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6693000197410583},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.351500004529953},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.263700008392334}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.03812","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.03812","pdf_url":"https://arxiv.org/pdf/2601.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.03812","doi":"https://doi.org/10.48550/arxiv.2601.03812","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03812","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.03812","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.03812","pdf_url":"https://arxiv.org/pdf/2601.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7119474229.pdf","grobid_xml":"https://content.openalex.org/works/W7119474229.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128190501","https://openalex.org/W7118014044","https://openalex.org/W7120115509","https://openalex.org/W7162428099","https://openalex.org/W4406458155","https://openalex.org/W4414453671","https://openalex.org/W4391450222","https://openalex.org/W7213534634","https://openalex.org/W6902309181","https://openalex.org/W4400771375"],"abstract_inverted_index":{"The":[0,99,127,152],"rapid":[1],"development":[2],"of":[3,34,91,105,113,120,144,154],"large":[4],"language":[5],"models":[6,44,96,191],"has":[7],"led":[8],"to":[9,56,67,137,160,171,186],"an":[10,32,103],"increase":[11],"in":[12],"AI-generated":[13],"text,":[14],"with":[15,115],"students":[16],"increasingly":[17],"using":[18],"LLM-generated":[19],"content":[20],"as":[21,181],"their":[22],"own":[23],"work,":[24,168],"which":[25],"violates":[26],"academic":[27],"integrity.":[28],"This":[29,71],"paper":[30],"presents":[31],"evaluation":[33,150],"AI":[35],"text":[36],"detection":[37],"methods,":[38],"including":[39],"both":[40],"traditional":[41],"machine":[42],"learning":[43,95],"and":[45,53,61,140,163,175,192,198],"transformer-based":[46],"architectures.":[47],"We":[48,183],"utilize":[49,176],"two":[50],"datasets,":[51],"HC3":[52],"DAIGT":[54],"v2,":[55],"build":[57],"a":[58,63,87,110],"unified":[59],"benchmark":[60],"apply":[62],"topic-based":[64],"data":[65],"split":[66],"prevent":[68],"information":[69],"leakage.":[70],"approach":[72],"ensures":[73],"robust":[74],"generalization":[75],"across":[76],"unseen":[77],"domains.":[78],"Our":[79],"experiments":[80],"show":[81],"that":[82,130],"TF-IDF":[83],"logistic":[84],"regression":[85],"achieves":[86,102,109],"reasonable":[88],"baseline":[89],"accuracy":[90,104,112],"82.87%.":[92],"However,":[93],"deep":[94],"outperform":[97],"it.":[98],"BiLSTM":[100],"classifier":[101],"88.86%,":[106],"while":[107],"DistilBERT":[108],"similar":[111],"88.11%":[114],"the":[116,123,142],"highest":[117],"ROC-AUC":[118],"score":[119],"0.96,":[121],"demonstrating":[122],"strongest":[124],"overall":[125],"performance.":[126],"results":[128],"indicate":[129],"contextual":[131],"semantic":[132],"modeling":[133],"is":[134],"significantly":[135],"superior":[136],"lexical":[138],"features":[139],"highlight":[141],"importance":[143],"mitigating":[145],"topic":[146],"memorization":[147],"through":[148],"appropriate":[149],"protocols.":[151],"limitations":[153],"this":[155],"work":[156],"are":[157],"primarily":[158],"related":[159],"dataset":[161,173],"diversity":[162,174],"computational":[164],"constraints.":[165],"In":[166],"future":[167],"we":[169],"plan":[170,185],"expand":[172],"parameter-efficient":[177],"fine-tuning":[178],"methods":[179],"such":[180],"LoRA.":[182],"also":[184],"explore":[187],"smaller":[188],"or":[189],"distilled":[190],"employ":[193],"more":[194],"efficient":[195],"batching":[196],"strategies":[197],"hardware-aware":[199],"optimization.":[200]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-09T00:00:00"}