{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T08:44:07Z","timestamp":1787906647835,"version":"build-2784847793"},"reference-count":263,"publisher":"MIT Press","issue":"1","license":[{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The remarkable ability of large language models (LLMs) to comprehend, interpret, and generate complex language has rapidly integrated LLM-generated text into various aspects of daily life, where users increasingly accept it. However, the growing reliance on LLMs underscores the urgent need for effective detection mechanisms to identify LLM-generated text. Such mechanisms are critical to mitigating misuse and safeguarding domains like artistic expression and social networks from potential negative consequences. LLM-generated text detection, conceptualized as a binary classification task, seeks to determine whether an LLM produced a given text. Recent advances in this field stem from innovations in watermarking techniques, statistics-based detectors, and neural-based detectors. Human-assisted methods also play a crucial role. In this survey, we consolidate recent research breakthroughs in this field, emphasizing the urgent need to strengthen detector research. Additionally, we review existing datasets, highlighting their limitations and developmental requirements. Furthermore, we examine various LLM-generated text detection paradigms, shedding light on challenges like out-of-distribution problems, potential attacks, real-world data issues, and ineffective evaluation frameworks. Finally, we outline intriguing directions for future research in LLM-generated text detection to advance responsible artificial intelligence. This survey aims to provide a clear and comprehensive introduction for newcomers while offering seasoned researchers valuable updates in the field.1<\/jats:p>","DOI":"10.1162\/coli_a_00549","type":"journal-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T14:21:46Z","timestamp":1736518906000},"page":"275-338","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":171,"title":["A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions"],"prefix":"10.1162","volume":"51","author":[{"given":"Junchao","family":"Wu","sequence":"first","affiliation":[{"name":"University of Macau, NLP2CT Lab, Faculty of Science and Technology, Institute of Collaborative Innovation. nlp2ct.junchao@gmail.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Macau, NLP2CT Lab, Faculty of Science and Technology, Institute of Collaborative Innovation. nlp2ct.shuyang@gmail.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runzhe","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of Macau, NLP2CT Lab, Faculty of Science and Technology, Institute of Collaborative Innovation. nlp2ct.runzhe@gmail.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulin","family":"Yuan","sequence":"additional","affiliation":[{"name":"University of Macau, Department of Chinese Language and Literature, Faculty of Arts and Humanities. yulinyuan@um.edu.mo"},{"name":"Peking University, Department of Chinese Language and Literature, Faculty of Humanities. yuanyl@pku.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lidia Sam","family":"Chao","sequence":"additional","affiliation":[{"name":"University of Macau, NLP2CT Lab, Faculty of Science and Technology, State Key Laboratory of Internet of Things for Smart City. lidiasc@um.edu.mo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"University of Macau, NLP2CT Lab, Faculty of Science and Technology, Institute of Collaborative Innovation. derekfw@um.edu.mo"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2025,3,15]]},"reference":[{"key":"2025032113510667500_bib1","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/SP40001.2021.00083","article-title":"Adversarial Watermarking Transformer: Towards tracing text provenance with data hiding","volume-title":"42nd IEEE Symposium on Security and Privacy, SP 2021","author":"Abdelnabi","year":"2021"},{"key":"2025032113510667500_bib2","first-page":"6586","article-title":"Demystifying neural fake news via linguistic feature-based interpretation","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022","author":"Aich","year":"2022"},{"key":"2025032113510667500_bib3","doi-asserted-by":"publisher","DOI":"10.52591\/lxai202312101","article-title":"Self-consuming generative models go MAD","volume":"abs\/2307.01850","author":"Alemohammad","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib4","article-title":"Model card and evaluations for Claude models","author":"Anthropic","year":"2023"},{"key":"2025032113510667500_bib5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.05871","article-title":"Towards a robust detection of language model generated text: Is ChatGPT that easy to detect?","author":"Antoun","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.13322","article-title":"From text to source: Results in detecting large language model-generated content","author":"Antoun","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib7","first-page":"1597","article-title":"Machine translation detection from monolingual web-text","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Arase","year":"2013"},{"key":"2025032113510667500_bib8","doi-asserted-by":"publisher","first-page":"41","DOI":"10.18653\/v1\/2023.acl-tutorials.6","article-title":"Retrieval-based language models and applications","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts)","author":"Asai","year":"2023"},{"key":"2025032113510667500_bib9","article-title":"Yelp dataset challenge: Review rating prediction","author":"Asghar","year":"2016","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib10","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0844-0","volume-title":"Word Frequency Distributions","author":"Baayen","year":"2001"},{"key":"2025032113510667500_bib11","article-title":"SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining","volume-title":"Proceedings of the International Conference on Language Resources and Evaluation, LREC 2010","author":"Baccianella","year":"2010"},{"key":"2025032113510667500_bib12","article-title":"Real or fake? Learning to discriminate machine from human generated text","author":"Bakhtin","year":"2019","journal-title":"CoRR"},{"key":"2025032113510667500_bib13","article-title":"Fast-DetectGPT: Efficient zero-shot detection of machine-generated text via conditional probability curvature","author":"Bao","year":"2023","journal-title":"arXiv preprint arXiv:2310.05130"},{"key":"2025032113510667500_bib14","article-title":"Mirostat: A neural text decoding algorithm that directly controls perplexity","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Basu","year":"2021"},{"issue":"3\/4","key":"2025032113510667500_bib15","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1147\/SJ.353.0313","article-title":"Techniques for data hiding","volume":"35","author":"Bender","year":"1996","journal-title":"IBM Systems Journal"},{"key":"2025032113510667500_bib16","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-319-41754-7_43","article-title":"Computer-generated text detection using machine learning: A systematic review","volume-title":"Natural Language Processing and Information Systems: 21st International Conference on Applications of Natural Language to Information Systems, NLDB 2016","author":"Beresneva","year":"2016"},{"key":"2025032113510667500_bib17","article-title":"Graph of thoughts: Solving elaborate problems with large language models","author":"Besta","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib18","doi-asserted-by":"publisher","first-page":"48","DOI":"10.18653\/v1\/2020.insights-1.7","article-title":"How effectively can machines defend against machine-generated fake news? An empirical study","volume-title":"Proceedings of the First Workshop on Insights from Negative Results in NLP, Insights 2020, Online, November 19, 2020","author":"Bhat","year":"2020"},{"key":"2025032113510667500_bib19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.03992","article-title":"ConDA: Contrastive domain adaptation for ai-generated text detection","author":"Bhattacharjee","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib20","article-title":"Fighting fire with fire: Can ChatGPT detect AI-generated text?","author":"Bhattacharjee","year":"2023","journal-title":"ArXiv preprint"},{"issue":"2","key":"2025032113510667500_bib21","doi-asserted-by":"publisher","first-page":"i\u201315","DOI":"10.1002\/j.2333-8504.2013.tb02331.x","article-title":"TOEFL11: A corpus of non-native English","volume":"2013","author":"Blanchard","year":"2013","journal-title":"ETS Research Report Series"},{"key":"2025032113510667500_bib22","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual","author":"Brown","year":"2020"},{"key":"2025032113510667500_bib23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.11503","article-title":"The age of synthetic realities: Challenges and opportunities","author":"Cardenuto","year":"2023","journal-title":"CoRR"},{"issue":"2","key":"2025032113510667500_bib24","doi-asserted-by":"publisher","DOI":"10.37074\/jalt.2023.6.2.12","article-title":"Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: The case of five AI content detection tools","volume":"6","author":"Chaka","year":"2023","journal-title":"Journal of Applied Learning and Teaching"},{"key":"2025032113510667500_bib25","doi-asserted-by":"publisher","first-page":"2206","DOI":"10.18653\/v1\/2023.emnlp-main.136","article-title":"Counter Turing Test (CT2): AI-generated text detection is not as easy as you may think - Introducing AI Detectability Index (ADI)","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","author":"Chakraborty","year":"2023"},{"key":"2025032113510667500_bib26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.04736","article-title":"On the possibilities of AI-generated text detection","author":"Chakraborty","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib27","article-title":"Dual contrastive learning: Text classification via label-aware data augmentation","author":"Chen","year":"2022","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib28","doi-asserted-by":"publisher","first-page":"13112","DOI":"10.18653\/v1\/2023.emnlp-main.810","article-title":"Token prediction as implicit classification to identify LLM-generated text","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","author":"Chen","year":"2023"},{"key":"2025032113510667500_bib29","article-title":"GPT-sentinel: Distinguishing human and ChatGPT generated content","author":"Chen","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib30","article-title":"FacTool: Factuality detection in generative AI\u2013A tool augmented framework for multi-task and multi-domain scenarios","volume":"abs\/2307.13528","author":"Chern","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib31","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1109\/APCCAS.1998.743799","article-title":"Electronic document data hiding technique using inter-character space","volume-title":"IEEE. APCCAS 1998. 1998 IEEE Asia-Pacific Conference on Circuits and Systems. Microelectronics and Integrating Systems. Proceedings (Cat. No. 98EX242)","author":"Chotikakamthorn","year":"1998"},{"key":"2025032113510667500_bib32","article-title":"PaLM: Scaling language modeling with pathways","volume":"abs\/2204.02311","author":"Chowdhery","year":"2022","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib33","article-title":"CNET secretly used AI on articles that didn\u2019t disclose that fact, staff say","author":"Christian","year":"2023","journal-title":"Futurism"},{"key":"2025032113510667500_bib34","doi-asserted-by":"publisher","first-page":"7282","DOI":"10.18653\/v1\/2021.acl-long.565","article-title":"All that\u2019s \u2018human\u2019 is not gold: Evaluating human evaluation of generated text","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Clark","year":"2021"},{"key":"2025032113510667500_bib35","doi-asserted-by":"publisher","first-page":"8440","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"Unsupervised cross-lingual representation learning at scale","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020","author":"Conneau","year":"2020"},{"key":"2025032113510667500_bib36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN54540.2023.10191322","article-title":"A deep fusion model for human $vs$. Machine-generated essay classification","volume-title":"International Joint Conference on Neural Networks, IJCNN 2023","author":"Corizzo","year":"2023"},{"key":"2025032113510667500_bib37","doi-asserted-by":"publisher","first-page":"148","DOI":"10.3115\/1073012.1073032","article-title":"A machine learning approach to the automatic evaluation of machine translation","volume-title":"Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics","author":"Corston-Oliver","year":"2001"},{"key":"2025032113510667500_bib38","doi-asserted-by":"publisher","first-page":"9928","DOI":"10.18653\/v1\/2023.findings-emnlp.665","article-title":"Do stochastic parrots have feelings too? Improving neural detection of synthetic text via emotion recognition","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Cowap","year":"2023"},{"key":"2025032113510667500_bib39","doi-asserted-by":"publisher","first-page":"70977","DOI":"10.1109\/ACCESS.2023.3294090","article-title":"Machine-generated text: A comprehensive survey of threat models and detection methods","volume":"11","author":"Crothers","year":"2023","journal-title":"IEEE Access"},{"key":"2025032113510667500_bib40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN55064.2022.9892269","article-title":"Adversarial robustness of neural-statistical features in detection of generative transformers","volume-title":"International Joint Conference on Neural Networks, IJCNN 2022","author":"Crothers","year":"2022"},{"key":"2025032113510667500_bib41","article-title":"ChatLaw: Open-source legal large language model with integrated external knowledge bases","author":"Cui","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.247","article-title":"Why can GPT learn in-context? Language models implicitly perform gradient descent as meta-optimizers","volume-title":"ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models","author":"Dai","year":"2023"},{"key":"2025032113510667500_bib43","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-319-78503-5_6","article-title":"Evaluation metrics and evaluation","author":"Dalianis","year":"2018","journal-title":"Clinical Text Mining: Secondary Use of Electronic Patient Records"},{"key":"2025032113510667500_bib44","article-title":"Parrot: Paraphrase generation for NLU","author":"Damodaran","year":"2021"},{"key":"2025032113510667500_bib45","article-title":"Efficient detection of LLM-generated texts with a Bayesian surrogate model","author":"Deng","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib46","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2023.101426","article-title":"ChatGPT or academic scientist? Distinguishing authorship with over 99% accuracy using off-the-shelf machine learning tools","author":"Desaire","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib47","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/v1\/n19-1423","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"2025032113510667500_bib48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.07689","article-title":"Detecting ChatGPT: A survey of the state of detecting ChatGPT-generated text","author":"Dhaini","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib49","article-title":"A survey for in-context learning","author":"Dong","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib50","doi-asserted-by":"publisher","first-page":"7250","DOI":"10.18653\/v1\/2022.acl-long.501","article-title":"Is GPT-3 text indistinguishable from human text? Scarecrow: A framework for scrutinizing machine text","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Dou","year":"2022"},{"key":"2025032113510667500_bib51","doi-asserted-by":"publisher","first-page":"189","DOI":"10.18653\/v1\/2020.emnlp-demos.25","article-title":"RoFT: A tool for evaluating human detection of machine-generated text","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Dugan","year":"2020"},{"key":"2025032113510667500_bib52","doi-asserted-by":"publisher","first-page":"12763","DOI":"10.1609\/aaai.v37i11.26501","article-title":"Real or fake text?: Investigating human ability to detect boundaries between human-written and machine-generated text","volume-title":"Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023","author":"Dugan","year":"2023"},{"issue":"6650","key":"2025032113510667500_bib53","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1126\/science.adh4451","article-title":"Art and the science of generative AI","volume":"380","author":"Epstein","year":"2023","journal-title":"Science"},{"issue":"5","key":"2025032113510667500_bib54","doi-asserted-by":"publisher","first-page":"e0251415","DOI":"10.1371\/journal.pone.0251415","article-title":"TweepFake: About detecting deepfake tweets","volume":"16","author":"Fagni","year":"2021","journal-title":"PLOS ONE"},{"key":"2025032113510667500_bib55","doi-asserted-by":"publisher","first-page":"3558","DOI":"10.18653\/v1\/P19-1346","article-title":"ELI5: Long form question answering","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Fan","year":"2019"},{"key":"2025032113510667500_bib56","doi-asserted-by":"publisher","first-page":"889","DOI":"10.18653\/v1\/P18-1082","article-title":"Hierarchical neural story generation","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Fan","year":"2018"},{"key":"2025032113510667500_bib57","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001","volume-title":"WordNet: An electronic lexical database","author":"Fellbaum","year":"1998"},{"key":"2025032113510667500_bib58","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1145\/3366424.3383110","article-title":"Explainable AI in industry: Practical challenges and lessons learned","volume-title":"Companion Proceedings of the Web Conference 2020","author":"Gade","year":"2020"},{"key":"2025032113510667500_bib59","article-title":"Unsupervised and distributional detection of machine-generated text","author":"Gall\u00e9","year":"2021","journal-title":"CoRR"},{"key":"2025032113510667500_bib60","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1145\/3501247.3531560","article-title":"On pushing DeepFake tweet detection capabilities to the limits","volume-title":"Proceedings of the 14th ACM Web Science Conference 2022","author":"Gambini","year":"2022"},{"key":"2025032113510667500_bib61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.05952","article-title":"LLM-as-a-coauthor: The challenges of detecting LLM-human mixcase","author":"Gao","year":"2024","journal-title":"CoRR"},{"key":"2025032113510667500_bib62","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/SPW.2018.00016","article-title":"Black-box generation of adversarial text sequences to evade deep learning classifiers","volume-title":"2018 IEEE Security and Privacy Workshops (SPW)","author":"Gao","year":"2018"},{"key":"2025032113510667500_bib63","doi-asserted-by":"publisher","first-page":"16477","DOI":"10.18653\/v1\/2023.acl-long.910","article-title":"RARR: Researching and revising what language models say, using language models","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Gao","year":"2023"},{"key":"2025032113510667500_bib64","doi-asserted-by":"publisher","first-page":"6894","DOI":"10.18653\/v1\/2021.emnlp-main.552","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Gao","year":"2021"},{"key":"2025032113510667500_bib65","doi-asserted-by":"publisher","first-page":"111","DOI":"10.18653\/v1\/P19-3019","article-title":"GLTR: Statistical detection and visualization of generated text","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations","author":"Gehrmann","year":"2019"},{"key":"2025032113510667500_bib66","article-title":"A survey on the possibilities & impossibilities of AI-generated text detection","author":"Ghosal","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"2025032113510667500_bib67","first-page":"23","article-title":"\u201cI slept like a baby\u201d: Using human traits to characterize deceptive ChatGPT and human text","volume-title":"Proceedings of the IACT - The 1st International Workshop on Implicit Author Characterization from Texts for Search and Retrieval held in conjunction with the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023)","author":"Giorgi","year":"2023"},{"key":"2025032113510667500_bib68","doi-asserted-by":"publisher","first-page":"5148","DOI":"10.18653\/v1\/2021.findings-acl.457","article-title":"Characterizing social spambots by their human traits","volume-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","author":"Giorgi","year":"2021"},{"issue":"11","key":"2025032113510667500_bib69","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"2025032113510667500_bib70","article-title":"Watermarking pre-trained language models with backdooring","author":"Gu","year":"2022","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib71","article-title":"How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection","author":"Guo","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib72","first-page":"2440","article-title":"Wiki-40B: Multilingual language model dataset","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Guo","year":"2020"},{"key":"2025032113510667500_bib73","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.07700","article-title":"AuthentiGPT: Detecting machine-generated text via black-box language models denoising","author":"Guo","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib74","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.11767","article-title":"Improving detection of ChatGPT-generated fake science using real publication text: Introducing xFakeBibs a supervised-learning network algorithm","author":"Hamed","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.09820","article-title":"Machine-made media: Monitoring the mobilization of machine-generated articles on misinformation and mainstream news websites","author":"Hanley","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib76","article-title":"Spotting LLMs with binoculars: Zero-shot detection of machine-generated text","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Hans","year":"2024"},{"key":"2025032113510667500_bib77","first-page":"91","article-title":"Empirical analysis of beam search curse and search errors with model errors in neural machine translation","volume-title":"Proceedings of the 24th Annual Conference of the European Association for Machine Translation","author":"He","year":"2023"},{"key":"2025032113510667500_bib78","article-title":"MGTBench: Benchmarking machine-generated text detection","author":"He","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib79","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.18653\/v1\/2024.acl-long.226","article-title":"Can watermarks survive translation? On the cross-lingual consistency of text watermark for large language models","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024","author":"He","year":"2024"},{"key":"2025032113510667500_bib80","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.08913","article-title":"A statistical Turing test for generative models","author":"Helm","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib81","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.08968","article-title":"Stochastic parrots looking for stochastic parrots: LLMs are easy to fine-tune and hard to detect with other LLMs","author":"Henrique","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib82","article-title":"The Goldilocks principle: Reading children\u2019s books with explicit memory representations","volume-title":"4th International Conference on Learning Representations, ICLR 2016, Conference Track Proceedings","author":"Hill","year":"2016"},{"key":"2025032113510667500_bib83","article-title":"The curious case of neural text degeneration","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Holtzman","year":"2020"},{"key":"2025032113510667500_bib84","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1609\/icwsm.v11i1.14976","article-title":"This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news","volume-title":"Proceedings of the International AAAI Conference on Web and Social Media","author":"Horne","year":"2017"},{"key":"2025032113510667500_bib85","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.03991","article-title":"SemStamp: A semantic watermark with paraphrastic robustness for text generation","author":"Hou","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib86","article-title":"RADAR: Robust AI-text detection via adversarial learning","author":"Hu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib87","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.13934","article-title":"Perception, performance, and detectability of conversational artificial intelligence across 32 university courses","volume":"abs\/2305.13934","author":"Ibrahim","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib88","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.18653\/v1\/2020.acl-main.164","article-title":"Automatic detection of generated text is easiest when humans are fooled","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Ippolito","year":"2020"},{"key":"2025032113510667500_bib89","first-page":"38","article-title":"Uniform information density effects on syntactic choice in Hindi","volume-title":"Proceedings of the Workshop on Linguistic Complexity and Natural Language Processing","author":"Jain","year":"2018"},{"key":"2025032113510667500_bib90","doi-asserted-by":"publisher","first-page":"2296","DOI":"10.18653\/v1\/2020.coling-main.208","article-title":"Automatic detection of machine generated text: A critical survey","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics","author":"Jawahar","year":"2020"},{"issue":"12","key":"2025032113510667500_bib91","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"2025032113510667500_bib92","doi-asserted-by":"publisher","first-page":"4163","DOI":"10.18653\/v1\/2020.findings-emnlp.372","article-title":"TinyBERT: Distilling BERT for natural language understanding","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Jiao","year":"2020"},{"key":"2025032113510667500_bib93","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.18653\/v1\/D19-1259","article-title":"PubMedQA: A dataset for biomedical research question answering","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Jin","year":"2019"},{"key":"2025032113510667500_bib94","doi-asserted-by":"publisher","first-page":"92","DOI":"10.18653\/v1\/2021.acl-demo.11","article-title":"CogIE: An information extraction toolkit for bridging texts and CogNet","volume-title":"Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL 2021 - System Demonstrations","author":"Jin","year":"2021"},{"issue":"1","key":"2025032113510667500_bib95","first-page":"1082","article-title":"Digital libraries: Advanced methods and technologies, digital collections","volume":"9","author":"Kalinichenko","year":"2003","journal-title":"D-Lib Magazine"},{"key":"2025032113510667500_bib96","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.18653\/v1\/N18-1149","article-title":"A dataset of peer reviews (PeerRead): Collection, insights and NLP applications","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Kang","year":"2018"},{"key":"2025032113510667500_bib97","doi-asserted-by":"publisher","first-page":"102274","DOI":"10.1016\/j.lindif.2023.102274","article-title":"ChatGPT for good? On opportunities and challenges of large language models for education","volume":"103","author":"Kasneci","year":"2023","journal-title":"Learning and Individual Differences"},{"key":"2025032113510667500_bib98","doi-asserted-by":"publisher","first-page":"5449","DOI":"10.18653\/v1\/2024.acl-long.298","article-title":"Threads of subtlety: Detecting machine-generated texts through discourse motifs","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024","author":"Kim","year":"2024"},{"key":"2025032113510667500_bib99","first-page":"17061","article-title":"A watermark for large language models","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Kirchenbauer","year":"2023"},{"key":"2025032113510667500_bib100","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.04634","article-title":"On the reliability of watermarks for large language models","author":"Kirchenbauer","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib101","unstructured":"Kitchenham, Barbara and StuartCharters. 2007. Guidelines for performing systematic literature reviews in software engineering. Technical Report, EBSE Technical Report EBSE-2007-01. pages 1\u201357. https:\/\/legacyfileshare.elsevier.com\/promis_misc\/525444systematicreviewsguide.pdf"},{"key":"2025032113510667500_bib102","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1162\/tacl_a_00023","article-title":"The NarrativeQA reading comprehension challenge","volume":"6","author":"Ko\u010disk\u00fd","year":"2018","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2025032113510667500_bib103","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.08369","article-title":"How you prompt matters! Even task-oriented constraints in instructions affect LLM-generated text detection","author":"Koike","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib104","article-title":"OUTFOX: LLM-generated essay detection through in-context learning with adversarially generated examples","author":"Koike","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib105","article-title":"Large language models are zero-shot reasoners","volume-title":"NeurIPS","author":"Kojima","year":"2022"},{"key":"2025032113510667500_bib106","article-title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","author":"Krishna","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib107","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2307.15593","article-title":"Robust distortion-free watermarks for language models","author":"Kuditipudi","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib108","article-title":"Robust distortion-free watermarks for language models","author":"Kuditipudi","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"2025032113510667500_bib109","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.00509","article-title":"Exploring semantic perturbations on Grover","author":"Kulkarni","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib110","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.03164","article-title":"J-Guard: Journalism guided adversarially robust detection of AI-generated news","author":"Kumarage","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib111","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.18653\/v1\/2023.findings-emnlp.94","article-title":"How reliable are AI-generated-text detectors? An assessment framework using evasive soft prompts","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Kumarage","year":"2023"},{"key":"2025032113510667500_bib112","article-title":"Illustrating reinforcement learning from human feedback (RLHF)","author":"Lambert","year":"2022","journal-title":"HuggingFace Blog"},{"key":"2025032113510667500_bib113","first-page":"27","article-title":"Detecting fake content with relative entropy scoring","volume-title":"Proceedings of the 2008 International Conference on Uncovering Plagiarism, Authorship and Social Software Misuse-Volume 377","author":"Lavergne","year":"2008"},{"key":"2025032113510667500_bib114","doi-asserted-by":"publisher","first-page":"10669","DOI":"10.18653\/v1\/2021.emnlp-main.834","article-title":"Pushing on text readability assessment: A transformer meets handcrafted linguistic features","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event","author":"Lee","year":"2021"},{"key":"2025032113510667500_bib115","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.18653\/v1\/2020.emnlp-main.120","article-title":"SLM: Learning a discourse language representation with sentence unshuffling","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Lee","year":"2020"},{"key":"2025032113510667500_bib116","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.15060","article-title":"Who wrote this code? Watermarking for code generation","author":"Lee","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib117","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.14072","article-title":"Origin tracing and detecting of LLMs","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib118","article-title":"Self-alignment with instruction backtranslation","author":"Li","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib119","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.13242","article-title":"Deepfake text detection in the wild","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib120","article-title":"Mutation-based adversarial attacks on neural text detectors","author":"Liang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib121","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100779","article-title":"GPT detectors are biased against non-native English writers","volume-title":"ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models","author":"Liang","year":"2023"},{"key":"2025032113510667500_bib122","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0063","article-title":"TaskMatrix.AI: Completing tasks by connecting foundation models with millions of APIs","volume":"abs\/2303.16434","author":"Liang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib123","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.11567","article-title":"Differentiate ChatGPT-generated and human-written medical texts","author":"Liao","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib124","doi-asserted-by":"publisher","first-page":"3214","DOI":"10.18653\/v1\/2022.acl-long.229","article-title":"TruthfulQA: Measuring how models mimic human falsehoods","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Lin","year":"2022"},{"key":"2025032113510667500_bib125","doi-asserted-by":"publisher","DOI":"10.7910\/DVN\/5QCCUU","article-title":"Climate Change Tweets Ids","author":"Littman","year":"2019"},{"key":"2025032113510667500_bib126","article-title":"A private watermark for large language models","author":"Liu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib127","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.06356","article-title":"A semantic invariant robust watermark for large language models","author":"Liu","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib128","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.07913","article-title":"A survey of text watermarking in the era of large language models","author":"Liu","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib129","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.18653\/v1\/2024.acl-long.103","article-title":"Does DetectGPT fully utilize perturbation? Bridging selective perturbation to fine-tuned contrastive learning detector would be better","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024","author":"Liu","year":"2024"},{"key":"2025032113510667500_bib130","article-title":"CoCo: Coherence-enhanced machine-generated text detection under data limitation with contrastive learning","author":"Liu","year":"2022","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib131","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"2025032113510667500_bib132","article-title":"ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models","author":"Liu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib133","article-title":"Check me if you can: Detecting ChatGPT-generated academic writing using CheckGPT","author":"Liu","year":"2023","journal-title":"ArXiv preprint"},{"issue":"S1","key":"2025032113510667500_bib134","doi-asserted-by":"publisher","first-page":"S97\u2013S97","DOI":"10.1121\/1.2003013","article-title":"Harpy, a connected speech recognition system","volume":"59","author":"Lowerre","year":"1976","journal-title":"The Journal of the Acoustical Society of America"},{"key":"2025032113510667500_bib135","article-title":"Large language models can be guided to evade AI-generated text detection","author":"Lu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib136","doi-asserted-by":"publisher","first-page":"5755","DOI":"10.18653\/v1\/2022.acl-long.395","article-title":"Unified structure generation for universal information extraction","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022","author":"Lu","year":"2022"},{"key":"2025032113510667500_bib137","doi-asserted-by":"publisher","first-page":"242","DOI":"10.18653\/v1\/2023.trustnlp-1.21","article-title":"GPTs don\u2019t keep secrets: Searching for backdoor watermark triggers in autoregressive language models","volume-title":"Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023)","author":"Lucas","year":"2023"},{"key":"2025032113510667500_bib138","doi-asserted-by":"publisher","first-page":"17538","DOI":"10.18653\/v1\/2024.emnlp-main.971","article-title":"Zero-shot detection of LLM-generated text using token cohesiveness","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024","author":"Ma","year":"2024"},{"key":"2025032113510667500_bib139","article-title":"Is this abstract generated by AI? A research for the gap between AI-generated scientific text and human-written scientific text","volume":"abs\/2301.10416","author":"Ma","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib140","article-title":"AI vs. human\u2013differentiation analysis of scientific content generation","author":"Ma","year":"2023","journal-title":"arXiv"},{"key":"2025032113510667500_bib141","doi-asserted-by":"publisher","first-page":"9960","DOI":"10.18653\/v1\/2023.emnlp-main.616","article-title":"Multitude: Large-scale multilingual machine-generated text detection benchmark","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","author":"Macko","year":"2023"},{"key":"2025032113510667500_bib142","doi-asserted-by":"publisher","first-page":"e46924","DOI":"10.2196\/46924","article-title":"Artificial intelligence can generate fraudulent but authentic-looking scientific medical articles: Pandora\u2019s box has been opened","volume":"25","author":"M\u00e1jovsky\u0300","year":"2023","journal-title":"Journal of Medical Internet Research"},{"key":"2025032113510667500_bib143","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.12970","article-title":"Raidar: geneRative AI Detection viA Rewriting","author":"Mao","year":"2024","journal-title":"CoRR"},{"key":"2025032113510667500_bib144","doi-asserted-by":"publisher","DOI":"10.31234\/osf.io\/mnyz8","article-title":"Linguistic markers of inherent AI deception and intentional human deception: Evidence from hotel reviews","author":"Markowitz","year":"2023","journal-title":"PsyArXiv preprint"},{"key":"2025032113510667500_bib145","unstructured":"McCarthy, Philip M.\n          \n          2005. An Assessment of the Range and Usefulness of Lexical Diversity Measures and the Potential of the Measure of Textual, Lexical Diversity (MTLD). Ph.D. thesis, The University of Memphis."},{"key":"2025032113510667500_bib146","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.05341","article-title":"Classification of human- and AI-generated texts: Investigating features for ChatGPT","volume":"abs\/2308.05341","author":"Mindner","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib147","doi-asserted-by":"publisher","first-page":"103006","DOI":"10.1016\/j.cose.2022.103006","article-title":"The threat of offensive AI to organizations","author":"Mirsky","year":"2022","journal-title":"Computers & Security"},{"key":"2025032113510667500_bib148","first-page":"24950","article-title":"DetectGPT: Zero-shot machine-generated text detection using probability curvature","volume-title":"International Conference on Machine Learning, ICML 2023","author":"Mitchell","year":"2023"},{"key":"2025032113510667500_bib149","article-title":"ChatGPT or human? Detect and explain. Explaining decisions of machine learning model for detecting short ChatGPT-generated text","author":"Mitrovi\u0107","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib150","article-title":"SciGen: A dataset for reasoning-aware text generation from scientific tables","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Moosavi","year":"2021"},{"key":"2025032113510667500_bib151","doi-asserted-by":"publisher","first-page":"119","DOI":"10.18653\/v1\/2020.emnlp-demos.16","article-title":"TextAttack: A framework for adversarial attacks, data augmentation, and adversarial training in NLP","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2020 - Demos","author":"Morris","year":"2020"},{"key":"2025032113510667500_bib152","doi-asserted-by":"publisher","first-page":"190","DOI":"10.18653\/v1\/2023.trustnlp-1.17","article-title":"Distinguishing fact from fiction: A benchmark dataset for identifying machine-generated scientific papers in the LLM era","volume-title":"Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023)","author":"Mosca","year":"2023"},{"key":"2025032113510667500_bib153","doi-asserted-by":"publisher","first-page":"839","DOI":"10.18653\/v1\/N16-1098","article-title":"A corpus and cloze evaluation for deeper understanding of commonsense stories","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Mostafazadeh","year":"2016"},{"key":"2025032113510667500_bib154","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-4077382\/v1","article-title":"Contrasting linguistic patterns in human and LLM-generated text","author":"Mu\u00f1oz-Ortiz","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib155","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.05773","article-title":"DeepTextMark: Deep learning based text watermarking for detection of large language model generated text","author":"Munyer","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib156","doi-asserted-by":"publisher","DOI":"10.2196\/30642","article-title":"Covid-19 vaccine hesitancy on social media: Building a public Twitter dataset of anti-vaccine content, vaccine misinformation and conspiracies. 2021; 1\u201310","author":"Muric","year":"2021","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib157","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1007\/s10462-019-09716-5","article-title":"Deep learning-based breast cancer classification through medical imaging modalities: State of the art and research challenges","volume":"53","author":"Murtaza","year":"2020","journal-title":"Artificial Intelligence Review"},{"key":"2025032113510667500_bib158","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.18653\/v1\/D18-1206","article-title":"Don\u2019t give me the details, just the summary! Topic-aware convolutional neural networks for extreme summarization","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Narayan","year":"2018"},{"key":"2025032113510667500_bib159","doi-asserted-by":"publisher","first-page":"22340","DOI":"10.18653\/v1\/2024.emnlp-main.1246","article-title":"SimLLM: Detecting sentences generated by large language models using similarity between the generation and its re-generation","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024","author":"Nguyen-Son","year":"2024"},{"key":"2025032113510667500_bib160","article-title":"Language model detectors are easily optimized against","volume-title":"The Twelfth International Conference on Learning Representations","author":"Nicks","year":"2023"},{"key":"2025032113510667500_bib161","unstructured":"OpenAI. 2023. GPT-4 technical report. CoRR, abs\/2303.08774. 10.48550\/arXiv.2303.08774"},{"key":"2025032113510667500_bib162","article-title":"Detecting LLM-generated text in computing education: A comparative study for ChatGPT cases","author":"Orenstrakh","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib163","article-title":"Training language models to follow instructions with human feedback, 2022","volume":"abs\/2203.02155","author":"Ouyang","year":"2022","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib164","first-page":"1233","article-title":"Threat scenarios and best practices to detect neural fake news","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Pagnoni","year":"2022"},{"key":"2025032113510667500_bib165","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.00412","article-title":"Hidding the ghostwriters: An adversarial evaluation of AI-generated student essay detection","author":"Peng","year":"2024","journal-title":"CoRR"},{"key":"2025032113510667500_bib166","article-title":"Many bioinformatics programming tasks can be automated with ChatGPT","author":"Piccolo","year":"2023","journal-title":"ArXiv preprint"},{"issue":"6","key":"2025032113510667500_bib167","first-page":"735","article-title":"WhiteSteg: A new scheme in information hiding using text steganography","volume":"7","author":"Por","year":"2008","journal-title":"WSEAS Transactions on Computers"},{"issue":"5","key":"2025032113510667500_bib168","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1016\/J.JSS.2011.12.023","article-title":"UniSpaChi: A text-based data hiding method using Unicode space characters","volume":"85","author":"Por","year":"2012","journal-title":"Journal of Systems and Software"},{"key":"2025032113510667500_bib169","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00653-1","article-title":"Generative AI entails a credit\u2013blame asymmetry","author":"Porsdam Mann","year":"2023","journal-title":"ArXiv preprint"},{"issue":"6","key":"2025032113510667500_bib170","doi-asserted-by":"publisher","DOI":"10.22161\/ijtle.2.6.4","article-title":"The effectiveness of free software for detecting AI-generated writing","volume":"2","author":"Price","year":"2023","journal-title":"International Journal of Teaching, Learning and Education"},{"issue":"3","key":"2025032113510667500_bib171","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MSECP.2003.1203220","article-title":"Hide and seek: An introduction to steganography","volume":"1","author":"Provos","year":"2003","journal-title":"IEEE Security & Privacy"},{"key":"2025032113510667500_bib172","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1109\/SP46215.2023.10179387","article-title":"Deepfake text detection: Limitations and opportunities","volume-title":"44th IEEE Symposium on Security and Privacy, SP 2023","author":"Pu","year":"2023"},{"key":"2025032113510667500_bib173","doi-asserted-by":"publisher","first-page":"4799","DOI":"10.18653\/v1\/2023.findings-emnlp.318","article-title":"On the zero-shot generalization of machine-generated text detectors","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Pu","year":"2023"},{"issue":"10","key":"2025032113510667500_bib174","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: A survey","volume":"63","author":"Qiu","year":"2020","journal-title":"Science China Technological Sciences"},{"key":"2025032113510667500_bib175","doi-asserted-by":"publisher","first-page":"727","DOI":"10.18653\/v1\/2023.bea-1.58","article-title":"Beyond black box AI generated plagiarism detection: From sentence to document level","volume-title":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications, BEA@ACL 2023","author":"Quidwai","year":"2023"},{"issue":"8","key":"2025032113510667500_bib176","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"2025032113510667500_bib177","first-page":"140:1\u2013140:67","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"2025032113510667500_bib178","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.18653\/v1\/D16-1264","article-title":"SQuAD: 100,000+ questions for machine comprehension of text","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Rajpurkar","year":"2016"},{"key":"2025032113510667500_bib179","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.18653\/v1\/P19-1103","article-title":"Generating natural language adversarial examples through probability weighted word saliency","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Ren","year":"2019"},{"key":"2025032113510667500_bib180","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1145\/2938503.2938510","article-title":"Content-preserving text watermarking through Unicode homoglyph substitution","volume-title":"Proceedings of the 20th International Database Engineering & Applications Symposium, IDEAS 2016","author":"Rizzo","year":"2016"},{"key":"2025032113510667500_bib181","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.18653\/v1\/2022.naacl-main.88","article-title":"Cross-domain detection of GPT-2-generated technical text","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Rodriguez","year":"2022"},{"key":"2025032113510667500_bib182","article-title":"Can AI-generated text be reliably detected?","author":"Sadasivan","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib183","doi-asserted-by":"publisher","first-page":"110273","DOI":"10.1016\/j.knosys.2023.110273","article-title":"Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities","volume":"263","author":"Saeed","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"2025032113510667500_bib184","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-031-42448-9_11","article-title":"Supervised machine-generated text detectors: Family and scale matters","volume-title":"International Conference of the Cross-Language Evaluation Forum for European Languages","author":"Sarvazyan","year":"2023"},{"key":"2025032113510667500_bib185","first-page":"1","article-title":"Classification of human- and AI-generated texts for English, French, German, and Spanish","volume-title":"Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023)","author":"Schaaff","year":"2023"},{"key":"2025032113510667500_bib186","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.16992","article-title":"How well can machine-generated texts be identified and can language models be trained to avoid identification?","author":"Schneider","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib187","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ArXiv preprint"},{"issue":"2","key":"2025032113510667500_bib188","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1162\/coli_a_00380","article-title":"The limitations of stylometry for detecting machine-generated fake news","volume":"46","author":"Schuster","year":"2020","journal-title":"Computational Linguistics"},{"key":"2025032113510667500_bib189","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.04537","article-title":"Long-form analogies generated by ChatGPT lack human-like psycholinguistic properties","author":"Seals","year":"2023","journal-title":"CoRR"},{"issue":"10","key":"2025032113510667500_bib190","doi-asserted-by":"publisher","first-page":"110","DOI":"10.14569\/IJACSA.2023.01410110","article-title":"Detecting and unmasking AI-generated texts through explainable artificial intelligence using stylistic features","volume":"14","author":"Shah","year":"2023","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"2025032113510667500_bib191","article-title":"A simple but tough-to-beat data augmentation approach for natural language understanding and generation","author":"Shen","year":"2020","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib192","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.15324","article-title":"Model evaluation for extreme risks","author":"Shevlane","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib193","doi-asserted-by":"publisher","first-page":"164","DOI":"10.18653\/v1\/2020.findings-emnlp.16","article-title":"Robustness to modification with shared words in paraphrase identification","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Shi","year":"2020"},{"key":"2025032113510667500_bib194","article-title":"Red teaming language model detectors with language models","author":"Shi","year":"2023","journal-title":"ArXiv preprint"},{"issue":"8022","key":"2025032113510667500_bib195","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1038\/s41586-024-07566-y","article-title":"AI models collapse when trained on recursively generated data","volume":"631","author":"Shumailov","year":"2024","journal-title":"Nature"},{"key":"2025032113510667500_bib196","doi-asserted-by":"publisher","DOI":"10.1007\/11941439_114","article-title":"Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation","volume-title":"Australian Conference on Artificial Intelligence","author":"Sokolova","year":"2006"},{"key":"2025032113510667500_bib197","article-title":"Release strategies and the social impacts of language models","volume":"abs\/1908.09203","author":"Solaiman","year":"2019","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib198","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.17650","article-title":"Comparing abstractive summaries generated by ChatGPT to real summaries through blinded reviewers and text classification algorithms","author":"Soni","year":"2023","journal-title":"CoRR"},{"issue":"4","key":"2025032113510667500_bib199","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/S41060-021-00299-5","article-title":"Detecting computer-generated disinformation","volume":"13","author":"Stiff","year":"2022","journal-title":"International Journal of Data Science and Analytics"},{"issue":"7947","key":"2025032113510667500_bib200","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1038\/d41586-023-00340-6","article-title":"What ChatGPT and generative AI mean for science","volume":"614","author":"Stokel-Walker","year":"2023","journal-title":"Nature"},{"key":"2025032113510667500_bib201","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.05540","article-title":"DetectLLM: Leveraging log rank information for zero-shot detection of machine-generated text","author":"Su","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib202","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.02731","article-title":"HC3 Plus: A semantic-invariant human ChatGPT comparison corpus","author":"Su","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib203","article-title":"ChatGPT: The end of online exam integrity?","author":"Susnjak","year":"2022","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib204","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Sutskever","year":"2014"},{"key":"2025032113510667500_bib205","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.07205","article-title":"The science of detecting LLM-generated texts","author":"Tang","year":"2023","journal-title":"CoRR"},{"issue":"4","key":"2025032113510667500_bib206","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1145\/3624725","article-title":"The science of detecting LLM-generated text","volume":"67","author":"Tang","year":"2024","journal-title":"Communications of the ACM"},{"key":"2025032113510667500_bib207","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.11470","article-title":"Did you train on my dataset? Towards public dataset protection with clean-label backdoor watermarking","author":"Tang","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib208","article-title":"Stanford Alpaca: An instruction-following LLaMa model","author":"Taori","year":"2023"},{"issue":"8","key":"2025032113510667500_bib209","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nature Medicine"},{"key":"2025032113510667500_bib210","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1145\/1161366.1161397","article-title":"The hiding virtues of ambiguity: Quantifiably resilient watermarking of natural language text through synonym substitutions","volume-title":"Proceedings of the 8th Workshop on Multimedia & Security, MM&Sec 2006","author":"Topkara","year":"2006"},{"key":"2025032113510667500_bib211","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971","article-title":"LLaMa: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib212","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.16746","article-title":"HANSEN: Human and AI spoken text benchmark for authorship analysis","author":"Tripto","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib213","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.14106","article-title":"ChatLog: Recording and analyzing ChatGPT across time","author":"Tu","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib214","article-title":"Intrinsic dimension estimation for robust detection of AI-generated texts","author":"Tulchinskii","year":"2023","journal-title":"ArXiv preprint"},{"issue":"1","key":"2025032113510667500_bib215","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3606274.3606276","article-title":"Attribution and obfuscation of neural text authorship: A data mining perspective","volume":"25","author":"Uchendu","year":"2023","journal-title":"SIGKDD Explorations Newsletter"},{"key":"2025032113510667500_bib216","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.12934","article-title":"TOPROBERTA: Topology-aware authorship attribution of deepfake texts","author":"Uchendu","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib217","doi-asserted-by":"publisher","first-page":"8384","DOI":"10.18653\/v1\/2020.emnlp-main.673","article-title":"Authorship attribution for neural text generation","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Uchendu","year":"2020"},{"key":"2025032113510667500_bib218","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v11i1.27557","article-title":"Does human collaboration enhance the accuracy of identifying LLM-generated deepfake texts?","author":"Uchendu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib219","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.18653\/v1\/2021.findings-emnlp.172","article-title":"TURINGBENCH: A benchmark environment for Turing test in the age of neural text generation","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2021","author":"Uchendu","year":"2021"},{"key":"2025032113510667500_bib220","article-title":"HowkGPT: Investigating the detection of ChatGPT-generated university student homework through context-aware perplexity analysis","author":"Vasilatos","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib221","doi-asserted-by":"publisher","first-page":"923","DOI":"10.18653\/v1\/2023.findings-eacl.70","article-title":"How do decoding algorithms distribute information in dialogue responses?","volume-title":"Findings of the Association for Computational Linguistics: EACL 2023","author":"Venkatraman","year":"2023"},{"key":"2025032113510667500_bib222","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.06202","article-title":"GPT-who: An information density-based machine-generated text detector","author":"Venkatraman","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib223","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.15047","article-title":"Ghostbuster: Detecting text ghostwritten by large language models","author":"Verma","year":"2023","journal-title":"CoRR"},{"issue":"1","key":"2025032113510667500_bib224","doi-asserted-by":"publisher","first-page":"20220158","DOI":"10.1515\/opis-2022-0158","article-title":"The effectiveness of software designed to detect AI-generated writing: A comparison of 16 AI text detectors","volume":"7","author":"Walters","year":"2023","journal-title":"Open Information Science"},{"key":"2025032113510667500_bib225","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Wang","year":"2019"},{"key":"2025032113510667500_bib226","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.08903","article-title":"SeqXGPT: Sentence-level AI-generated text detection","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib227","doi-asserted-by":"publisher","first-page":"2894","DOI":"10.18653\/v1\/2024.acl-long.160","article-title":"Stumbling blocks: Stress testing the robustness of machine-generated text detectors under attacks","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024","author":"Wang","year":"2024"},{"key":"2025032113510667500_bib228","article-title":"M4: Multi-generator, multi-domain, and multi-lingual black-box machine-generated text detection","volume":"abs\/2305.14902","author":"Wang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib229","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.07401","article-title":"Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT","author":"Wang","year":"2023","journal-title":"CoRR"},{"issue":"1","key":"2025032113510667500_bib230","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s40979-023-00146-z","article-title":"Testing of detection tools for AI-generated text","volume":"19","author":"Weber-Wulff","year":"2023","journal-title":"International Journal for Educational Integrity"},{"key":"2025032113510667500_bib231","doi-asserted-by":"publisher","first-page":"5191","DOI":"10.18653\/v1\/2021.acl-long.404","article-title":"A cognitive regularizer for language modeling","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1\u20136, 2021","author":"Wei","year":"2021"},{"key":"2025032113510667500_bib232","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025032113510667500_bib233","article-title":"Ethical and social risks of harm from language models (2021)","author":"Weidinger","year":"2021","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib234","article-title":"Towards an understanding and explanation for mixed-initiative artificial scientific text detection","author":"Weng","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib235","article-title":"Large language models and copyright","author":"Wikipedia","year":"2023"},{"key":"2025032113510667500_bib236","article-title":"Lexical steganography through adaptive modulation of the word choice hash","author":"Winstein","year":"1998"},{"key":"2025032113510667500_bib237","article-title":"Attacking neural text detectors","author":"Wolff","year":"2020","journal-title":"CoRR"},{"key":"2025032113510667500_bib238","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.04286","article-title":"Who wrote this? The key to zero-shot LLM-generated text detection is GECScore","author":"Wu","year":"2024","journal-title":"CoRR"},{"key":"2025032113510667500_bib239","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.23746","article-title":"DetectRL: Benchmarking LLM-generated text detection in real-world scenarios","author":"Wu","year":"2024","journal-title":"CoRR"},{"key":"2025032113510667500_bib240","doi-asserted-by":"publisher","first-page":"2113","DOI":"10.18653\/v1\/2023.findings-emnlp.139","article-title":"LLMDet: A third party large language models generated text detection tool","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Wu","year":"2023"},{"issue":"3","key":"2025032113510667500_bib241","first-page":"541","article-title":"Reversible natural language watermarking using synonym substitution and arithmetic coding","volume":"55","author":"Xiang","year":"2018","journal-title":"Computers, Materials & Continua"},{"issue":"2","key":"2025032113510667500_bib242","first-page":"125","article-title":"Detection of AI-generated essays in writing assessment","volume":"65","author":"Yan","year":"2023","journal-title":"Psychological Testing and Assessment Modeling"},{"key":"2025032113510667500_bib243","doi-asserted-by":"publisher","first-page":"5065","DOI":"10.18653\/v1\/2021.acl-long.393","article-title":"ConSERT: A contrastive framework for self-supervised sentence representation transfer","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Yan","year":"2021"},{"key":"2025032113510667500_bib244","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000250","article-title":"Is ChatGPT involved in texts? Measure the Polish ratio to detect ChatGPT-generated text","author":"Yang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib245","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.08883","article-title":"Watermarking text generated by black-box language models","author":"Yang","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib246","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.17359","article-title":"DNA-GPT: Divergent n-gram analysis for training-free detection of GPT-generated text","author":"Yang","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib247","doi-asserted-by":"publisher","first-page":"11613","DOI":"10.1609\/aaai.v36i10.21415","article-title":"Tracing text provenance via context-aware lexical substitution","volume-title":"Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelfth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event","author":"Yang","year":"2022"},{"key":"2025032113510667500_bib248","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Yang","year":"2019"},{"key":"2025032113510667500_bib249","article-title":"Tree of thoughts: Deliberate problem solving with large language models, May 2023","volume":"abs\/2305.10601","author":"Yao","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib250","first-page":"11941","article-title":"Break-it-fix-it: Unsupervised learning for program repair","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","author":"Yasunaga","year":"2021"},{"key":"2025032113510667500_bib251","doi-asserted-by":"publisher","first-page":"2092","DOI":"10.18653\/v1\/2023.acl-long.117","article-title":"Robust multi-bit natural language watermarking through invariant features","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023","author":"Yoo","year":"2023"},{"key":"2025032113510667500_bib252","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.12008","article-title":"CHEAT: A large-scale dataset for detecting ChatGPT-written abstracts","author":"Yu","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib253","doi-asserted-by":"publisher","first-page":"15838","DOI":"10.18653\/v1\/2024.emnlp-main.885","article-title":"Text fluoroscopy: Detecting LLM-generated text through intrinsic features","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024","author":"Yu","year":"2024"},{"key":"2025032113510667500_bib254","article-title":"GPT paternity test: GPT generated text detection with GPT genetic inheritance","author":"Yu","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib255","doi-asserted-by":"publisher","first-page":"4791","DOI":"10.18653\/v1\/P19-1472","article-title":"HellaSwag: Can a machine really finish your sentence?","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Zellers","year":"2019"},{"key":"2025032113510667500_bib256","first-page":"9051","article-title":"Defending against neural fake news","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Zellers","year":"2019"},{"key":"2025032113510667500_bib257","article-title":"Towards automatic boundary detection for human\u2013AI hybrid essay in education","author":"Zeng","year":"2023","journal-title":"arXiv preprint arXiv:"},{"key":"2025032113510667500_bib258","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.12362","article-title":"REMARK-LLM: A robust and efficient watermarking framework for generative large language models","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib259","article-title":"Siren\u2019s song in the AI ocean: A survey on hallucination in large language models","author":"Zhang","year":"2023","journal-title":"ArXiv preprint"},{"key":"2025032113510667500_bib260","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.12918","article-title":"Assaying on the robustness of zero-shot machine-generated text detectors","author":"Zhang","year":"2023","journal-title":"CoRR"},{"key":"2025032113510667500_bib261","first-page":"12697","article-title":"Calibrate before use: Improving few-shot performance of language models","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","author":"Zhao","year":"2021"},{"key":"2025032113510667500_bib262","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.18653\/v1\/2020.emnlp-main.193","article-title":"Neural deepfake detection with factual structure of text","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Zhong","year":"2020"},{"key":"2025032113510667500_bib263","doi-asserted-by":"publisher","first-page":"7470","DOI":"10.18653\/v1\/2023.emnlp-main.463","article-title":"Beat LLMs at their own game: Zero-shot LLM-generated text detection via querying ChatGPT","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","author":"Zhu","year":"2023"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/51\/1\/275\/2497295\/coli_a_00549.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/coli\/article-pdf\/51\/1\/275\/2497295\/coli_a_00549.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T14:19:39Z","timestamp":1742566779000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/51\/1\/275\/127462\/A-Survey-on-LLM-Generated-Text-Detection-Necessity"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":263,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3,15]]},"published-print":{"date-parts":[[2025,3,15]]}},"URL":"https:\/\/doi.org\/10.1162\/coli_a_00549","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]}}}