<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1405-5546</journal-id>
<journal-title><![CDATA[Computación y Sistemas]]></journal-title>
<abbrev-journal-title><![CDATA[Comp. y Sist.]]></abbrev-journal-title>
<issn>1405-5546</issn>
<publisher>
<publisher-name><![CDATA[Instituto Politécnico Nacional, Centro de Investigación en Computación]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1405-55462023000400921</article-id>
<article-id pub-id-type="doi">10.13053/cys-27-4-4778</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[PoSLemma: How Traditional Machine Learning and Linguistics Preprocessing Aid in Machine Generated Text Detection]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Jiménez]]></surname>
<given-names><![CDATA[Diana]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Cardoso-Moreno]]></surname>
<given-names><![CDATA[Marco A.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Aguilar-Canto]]></surname>
<given-names><![CDATA[Fernando]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Juárez-Gambino]]></surname>
<given-names><![CDATA[Omar]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Calvo]]></surname>
<given-names><![CDATA[Hiram]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Instituto Politécnico Nacional Centro de Investigación en Computación ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Mexico</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>12</month>
<year>2023</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>12</month>
<year>2023</year>
</pub-date>
<volume>27</volume>
<numero>4</numero>
<fpage>921</fpage>
<lpage>928</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1405-55462023000400921&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1405-55462023000400921&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1405-55462023000400921&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract: With the release of several Large Language Models (LLMs) to the public, concerns have emerged regarding their ethical implications and potential misuse. This paper proposes an approach to address the need for technologies that can distinguish between text sequences generated by humans and those produced by LLMs. The proposed method leverages traditional Natural Language Processing (NLP) feature extraction techniques focusing on linguistic properties, and traditional Machine Learning (ML) methods like Logistic Regression and Support Vector Machines (SVMs). We also compare this approach with an ensemble of Long-Short Term Memory (LSTM) networks, each analyzing different paradigms of Part of Speech (PoS) taggings. Our traditional ML models achieved F1 scores of 0.80 and 0.72 in the respective analyzed tasks.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Generative text detection]]></kwd>
<kwd lng="en"><![CDATA[text generation]]></kwd>
<kwd lng="en"><![CDATA[AuTexTification]]></kwd>
<kwd lng="en"><![CDATA[logistic regression]]></kwd>
<kwd lng="en"><![CDATA[support vector machine (SVM)]]></kwd>
<kwd lng="en"><![CDATA[classification]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Alexander]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Savvidou]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Alexander]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Who wrote this essay? Detecting AI-generated writing in second language education in higher education]]></article-title>
<source><![CDATA[Teaching English with Technology]]></source>
<year>2023</year>
<volume>23</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>25-43</page-range></nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Antoun]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[Baly]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Hajj]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[AraBERT: Transformer-based model for arabic language understanding]]></source>
<year>2020</year>
<conf-name><![CDATA[ 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection]]></conf-name>
<conf-loc> </conf-loc>
<page-range>9-15</page-range></nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Brown]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Mann]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Ryder]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Subbiah]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Kaplan]]></surname>
<given-names><![CDATA[J. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Dhariwal]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Neelakantan]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Shyam]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Sastry]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Askell]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Agarwal]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Herbert-Voss]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Krueger]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Henighan]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Child]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Ramesh]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Ziegler]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Winter]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Hesse]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
</person-group>
<source><![CDATA[Language models are few-shot learners]]></source>
<year>2020</year>
<volume>33</volume>
<numero>159</numero>
<conf-name><![CDATA[ 34th Conference on Neural Information Processing Systems]]></conf-name>
<conf-loc> </conf-loc>
<issue>159</issue>
<page-range>1877-901</page-range></nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chowdhery]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Narang]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Devlin]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Bosma]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Mishra]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Roberts]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Barham]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Chung]]></surname>
<given-names><![CDATA[H. W.]]></given-names>
</name>
<name>
<surname><![CDATA[Sutton]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Gehrmann]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Schuh]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Shi]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Tsvyashchenko]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Maynez]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Rao]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Barnes]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Tay]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Shazeer]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Prabhakaran]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Reif]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Du]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
</person-group>
<source><![CDATA[PaLM: Scaling language modeling with pathways]]></source>
<year>2022</year>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Clark]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[August]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Serrano]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Haduong]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Gururangan]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Smith]]></surname>
<given-names><![CDATA[N. A.]]></given-names>
</name>
</person-group>
<source><![CDATA[All that&#8217;s &#8217;human&#8217; is not gold: Evaluating human evaluation of generated text]]></source>
<year>2021</year>
<volume>1</volume>
<conf-name><![CDATA[ 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing]]></conf-name>
<conf-loc> </conf-loc>
<page-range>7282-96</page-range></nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Devlin]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Chang]]></surname>
<given-names><![CDATA[M. W.]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Toutanova]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
</person-group>
<source><![CDATA[BERT: Pre-training of deep bidirectional transformers for language understanding]]></source>
<year>2019</year>
<volume>1</volume>
<conf-name><![CDATA[ Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies]]></conf-name>
<conf-date>2019</conf-date>
<conf-loc> </conf-loc>
<page-range>4171-86</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fagni]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Falchi]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Gambini]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Martella]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Tesconi]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[TweepFake: About detecting deepfake tweets]]></article-title>
<source><![CDATA[PLoS One]]></source>
<year>2021</year>
<volume>16</volume>
<numero>5</numero>
<issue>5</issue>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gehrmann]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Harvard]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Strobelt]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Rush]]></surname>
<given-names><![CDATA[A. M.]]></given-names>
</name>
</person-group>
<source><![CDATA[GLTR: Statistical detection and visualization of generated text]]></source>
<year>2019</year>
<conf-name><![CDATA[ 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations]]></conf-name>
<conf-loc> </conf-loc>
<page-range>111-6</page-range></nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Guo]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Jiang]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Nie]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Ding]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Yue]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ippolito]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Duckworth]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Callison-Burch]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Eck]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<source><![CDATA[Automatic detection of generated text is easiest when humans are fooled]]></source>
<year>2019</year>
<conf-name><![CDATA[ 58th Annual Meeting of the Association for Computational Linguistics]]></conf-name>
<conf-loc> </conf-loc>
<page-range>1808-22</page-range></nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kingma]]></surname>
<given-names><![CDATA[D. P.]]></given-names>
</name>
<name>
<surname><![CDATA[Ba]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[ADAM: A method for stochastic optimization]]></source>
<year>2014</year>
<conf-name><![CDATA[ International Conference on Learning Representations]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kumarage]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Garland]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Bhattacharjee]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Trapeznikov]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Ruston]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[Stylometric detection of AI-generated text in twitter timelines]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Leiser]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Eckhardt]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Knaeble]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Mädche]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Schwabe]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Sunyaev]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[From ChatGPT to FactGPT: A participatory design study to mitigate the effects of large language model hallucinations on users]]></source>
<year>2023</year>
<conf-name><![CDATA[ Mensch und Computer]]></conf-name>
<conf-date>2023</conf-date>
<conf-loc> </conf-loc>
<page-range>81-90</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lewis]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Goyal]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Ghazvininejad]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Mohamed]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Levy]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
<name>
<surname><![CDATA[Stoyanov]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
<name>
<surname><![CDATA[Zettlemoyer]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<source><![CDATA[BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension]]></source>
<year>2019</year>
<conf-name><![CDATA[ 58th Annual Meeting of the Association for Computational Linguistics]]></conf-name>
<conf-loc> </conf-loc>
<page-range>7871-80</page-range></nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Ott]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Goyal]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Du]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Joshi]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Levy]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
<name>
<surname><![CDATA[Lewis]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Zettlemoyer]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Stoyanov]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[RoBERTa: A robustly optimized BERT pretraining approach]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ma]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Yi]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Cheng]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Lu]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
</person-group>
<source><![CDATA[AI vs. human&#8211;differentiation analysis of scientific content generation]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mann]]></surname>
<given-names><![CDATA[W. C.]]></given-names>
</name>
<name>
<surname><![CDATA[Matthiessen]]></surname>
<given-names><![CDATA[C. M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Nigel: A systemic grammar for text generation]]></source>
<year>1983</year>
<publisher-loc><![CDATA[Marina del Rey ]]></publisher-loc>
<publisher-name><![CDATA[University of Southern California]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[McKeown]]></surname>
<given-names><![CDATA[K. R.]]></given-names>
</name>
</person-group>
<source><![CDATA[Text generation (Studies in natural language processing)]]></source>
<year>1992</year>
<publisher-name><![CDATA[Cambridge University Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mireshghallah]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Mattern]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Shokri]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Berg-Kirkpatrick]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[Smaller language models are better black-box machine-generated text detectors]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mitchell]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Khazatsky]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Manning]]></surname>
<given-names><![CDATA[C. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Finn]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
</person-group>
<source><![CDATA[DetectGPT: Zero-shot machine-generated text detection using probability curvature]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mitrovi&#263;]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Andreoletti]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Ayoub]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
</person-group>
<source><![CDATA[ChatGPT or human? Detect and explain. Explaining decisions of machine learning model for detecting short ChatGPT-generated text]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="">
<collab>OpenAI</collab>
<source><![CDATA[GPT-4 technical report]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Radford]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Narasimhan]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Salimans]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Sutskever]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<source><![CDATA[Improving language understanding by generative pre-training]]></source>
<year>2018</year>
<publisher-name><![CDATA[OpenAI]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Radford]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Child]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Luan]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Amodei]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Sutskever]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<source><![CDATA[Language models are unsupervised multitask learners]]></source>
<year>2019</year>
<volume>1</volume>
<numero>8</numero>
<issue>8</issue>
<page-range>9</page-range><publisher-name><![CDATA[OpenAI]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rodríguez]]></surname>
<given-names><![CDATA[J. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Hay]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Gros]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Shamsi]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Srinivasan]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
</person-group>
<source><![CDATA[Cross-domain detection of GPT-2-generated technical text]]></source>
<year>2022</year>
<conf-name><![CDATA[ Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies]]></conf-name>
<conf-date>2022</conf-date>
<conf-loc> </conf-loc>
<page-range>1213-33</page-range></nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sarvazyan]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[González]]></surname>
<given-names><![CDATA[J. Á.]]></given-names>
</name>
<name>
<surname><![CDATA[Franco]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Rangel]]></surname>
<given-names><![CDATA[F. M.]]></given-names>
</name>
<name>
<surname><![CDATA[Chulvi]]></surname>
<given-names><![CDATA[M. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Rosso]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<source><![CDATA[AuTexTification dataset (full data)]]></source>
<year>2023</year>
<publisher-name><![CDATA[Zenodo]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sarvazyan]]></surname>
<given-names><![CDATA[A. M.]]></given-names>
</name>
<name>
<surname><![CDATA[González]]></surname>
<given-names><![CDATA[J. Á.]]></given-names>
</name>
<name>
<surname><![CDATA[Franco-Salvador]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Rangel]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Chulvi]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Rosso]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Overview of AuTexTification at IberLEF 2023: Detection and attribution of machine-generated text in multiple domains]]></article-title>
<source><![CDATA[Procesamiento del Lenguaje Natural]]></source>
<year>2023</year>
<numero>71</numero>
<issue>71</issue>
<page-range>275-88</page-range></nlm-citation>
</ref>
<ref id="B28">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Scao]]></surname>
<given-names><![CDATA[T. L.]]></given-names>
</name>
<name>
<surname><![CDATA[Fan]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Akiki]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Pavlick]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Ili&#263;]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Hesslow]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Castagné]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Luccioni]]></surname>
<given-names><![CDATA[A. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Yvon]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Gallé]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Tow]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Rush]]></surname>
<given-names><![CDATA[A. M.]]></given-names>
</name>
<name>
<surname><![CDATA[Biderman]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Webson]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Ammanamanchi]]></surname>
<given-names><![CDATA[P. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Sagot]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Muennighoff]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Villanova-Moral]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Ruwase]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
</person-group>
<source><![CDATA[BLOOM: A 176B-parameter open-access multilingual language model]]></source>
<year>2022</year>
<publisher-name><![CDATA[BigScience Workshop]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B29">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Shijaku]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Canhasi]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[ChatGPT generated text detection]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B30">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Solaiman]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Brundage]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Clark]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Askell]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Herbert-Voss]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Radford]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Krueger]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[J. W.]]></given-names>
</name>
<name>
<surname><![CDATA[Kreps]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[McCain]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Newhouse]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Blazakis]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[McGuffie]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Release strategies and the social impacts of language models]]></source>
<year>2019</year>
<publisher-name><![CDATA[OpenIA Report]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B31">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tourille]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Sow]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Popescu]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Automatic detection of bot-generated tweets]]></source>
<year>2022</year>
<conf-name><![CDATA[ 1st International Workshop on Multimedia AI against Disinformation]]></conf-name>
<conf-loc> </conf-loc>
<page-range>44-51</page-range></nlm-citation>
</ref>
<ref id="B32">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Uchendu]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Le]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Shu]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
</person-group>
<source><![CDATA[Authorship attribution for neural text generation]]></source>
<year>2020</year>
<conf-name><![CDATA[ Conference on Empirical Methods in Natural Language Processing (EMNLP)]]></conf-name>
<conf-date>2020</conf-date>
<conf-loc> </conf-loc>
<page-range>8384-95</page-range></nlm-citation>
</ref>
<ref id="B33">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zaitsu]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[Jin]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Distinguishing ChatGPT (-3.5,-4)-generated and human-written papers through Japanese stylometric analysis]]></article-title>
<source><![CDATA[PLoS One]]></source>
<year>2023</year>
<volume>18</volume>
<numero>8</numero>
<issue>8</issue>
</nlm-citation>
</ref>
<ref id="B34">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zellers]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Holtzman]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Rashkin]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Bisk]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Farhadi]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Roesner]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Choi]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Defending against neural fake news]]></source>
<year>2019</year>
<volume>32</volume>
<numero>812</numero>
<conf-name><![CDATA[ 33rd International Conference on Neural Information Processing Systems]]></conf-name>
<conf-loc> </conf-loc>
<issue>812</issue>
<page-range>9054-65</page-range></nlm-citation>
</ref>
<ref id="B35">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhan]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[He]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Stenetorp]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<source><![CDATA[G3Detector: General GPT-generated text detector]]></source>
<year>2023</year>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
