Elamur Research⌕
☰
home / papers / 2025 / A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions

A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions

Summary

Text from LLMs such as GPT-4, Claude and PaLM now reads so much like human writing that people spot it only slightly better than chance. Commercial detectors also make frequent mistakes and tend to label machine text as human. This opens the door to disinformation, scams and spam, and it lets synthetic text leak into future training corpora. The authors treat detection as a binary decision: was a given text produced by an LLM or not? They then review the field systematically. They explain how LLMs generate text, summarise known linguistic differences between machine and human writing, and assess existing datasets and benchmarks along with their shortcomings. They group detectors into four families: watermarking, statistics-based, neural-based and human-assisted methods. The survey's main contribution is a structured account of open problems. These are out-of-distribution generalisation, adversarial attacks, messy real-world data and evaluation setups that do not match practice. It ends with a research agenda and a public resource list, which makes it a useful starting point for newcomers and experienced researchers alike.

Key points

  • The authors cite Hanley and Durumeric (2023), who reported that the volume of machine-written news stories on mainstream websites grew by 55.4% between January 2022 and May 2023. Over the same period, misinformation sites showed a 457% rise.
  • Reported differences between the two kinds of text:
    • LLM output is roughly twice as long as human text but uses a narrower vocabulary.
    • It contains more nouns, verbs, determiners, auxiliaries and coordinating conjunctions.
    • It contains fewer adverbs and less punctuation, and it carries weaker emotional intensity.
  • Chakraborty et al. (2023) argue that even GPT-3.5-Turbo and GPT-4 output remains detectable. They also propose an AI Detectability Index for ranking models.
  • The proposed future directions are:
    • detecting mixed or human-edited text;
    • checking whether training data is truly human-written;
    • building evaluation frameworks that reflect real-world use;
    • adding fact verification through knowledge bases or search engines.
  • Resources are collected at github.com/NLP2CT/LLM-generated-Text-Detection. The paper is published under CC BY-NC-ND 4.0.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Natural language processing

Cited by

75 papers of our library cite it (of the 140884 whose bibliographies we read); 4 of them have a page here, 71 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00549

@article{wu2025survey,
  title = {{A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions}},
  author = {Wu, Junchao and Yang, Shu and Zhan, Runzhe and Yuan, Yulin and Chao, Lidia Sam and Wong, Derek Fai},
  journal = {Computational Linguistics},
  year = {2025},
  doi = {10.1162/coli\_a\_00549},
  url = {https://doi.org/10.1162/coli_a_00549}
}

References

98 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abdelnabi, Sahar and Mario Fritz. 2021. Adversarial Watermarking Transformer: Towards tracing text provenance with data hiding. In 42nd IEEE Symposium on Security and Privacy, SP 2021, pages 121–140. https://doi.org/10.1109/SP40001.2021.00083 Aich, Ankit, Souvik Bhattacharya, and Natalie Parde. 202… ↗
  2. Alemohammad, Sina, Josue Casco-Rodriguez, Lorenzo Luzi, Ahmed Imtiaz Humayun, Hossein Babaei, Daniel LeJeune, Ali Siahkoohi, and Richard G. Baraniuk. 2023. Self-consuming generative models go MAD. CoRR, abs/2307.01850. https://doi.org/10.52591/lxai202312101 Anthropic. 2023. Model card and evaluatio… ↗
  3. Asai, Akari, Sewon Min, Zexuan Zhong, and Danqi Chen. 2023. Retrieval-based language models and applications. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts), pages 41–46. https://doi.org/10.18653/v1/2023.acl-tutorials.6 Asgh… ↗
  4. Baayen, R. Harald. 2001. Word Frequency Distributions, volume 18. Springer Science & Business Media. https://doi.org/10.1007/978-94-010-0844-0 Baccianella, Stefano, Andrea Esuli, and Fabrizio Sebastiani. 2010. SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining.… — [doi:10.1007/978-94-010-0844-0](https://doi.org/10.1007/978-94-010-0844-0) ↗
  5. Bakhtin, Anton, Sam Gross, Myle Ott, Yuntian Deng, Marc’Aurelio Ranzato, and Arthur Szlam. 2019. Real or fake? Learning to discriminate machine from human generated text. CoRR, abs/1906.03351. — [arXiv:1906.03351](https://arxiv.org/abs/1906.03351) find
  6. Bao, Guangsheng, Yanbin Zhao, Zhiyang Teng, Linyi Yang, and Yue Zhang. 2023. Fast-DetectGPT: Efficient zero-shot detection of machine-generated text via conditional probability curvature. arXiv preprint arXiv:2310.05130, abs/2310.05130. find our card
  7. Basu, Sourya, Govardana Sachitanandam Ramachandran, Nitish Shirish Keskar, and Lav R. Varshney. 2021. Mirostat: A neural text decoding algorithm that directly controls perplexity. In 9th International Conference on Learning Representations, ICLR 2021, OpenReview.net. find
  8. Bender, Walter, Daniel Gruhl, Norishige Morimoto, and Anthony Lu. 1996. Techniques for data hiding. IBM Systems Journal, 35(3/4):313–336. https://doi.org/10.1147/SJ.353.0313 Beresneva, Daria. 2016. Computer-generated text detection using machine learning: A systematic review. In Natural Language Pr… ↗
  9. Bhat, Meghana Moorthy and Srinivasan Parthasarathy. 2020. How effectively can machines defend against machine-generated fake news? An empirical study. In Proceedings of the First Workshop on Insights from Negative Results in NLP, Insights 2020, Online, November 19, 2020, pages 48–53. https://doi.org… ↗
  10. Blanchard, Daniel, Joel Tetreault, Derrick Higgins, Aoife Cahill, and Martin Chodorow. 2013. TOEFL11: A corpus of non-native English. ETS Research Report Series, 2013(2):i–15. https://doi.org/10.1002/j.2333-8504.2013.tb02331.x Brown, Tom B., Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan,… — [doi:10.1002/j.2333-8504.2013.tb02331.x](https://doi.org/10.1002/j.2333-8504.2013.tb02331.x) ↗
  11. Chaka, Chaka. 2023. Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: The case of five AI content detection tools. Journal of Applied Learning and Teaching, 6(2). https://doi.org/10.37074/jalt.2023.6.2.12 Chakraborty, Megha, S. M. Towhidul Islam Tonmoy, S. M. Mehedi Za… ↗
  12. Chen, Yutian, Hao Kang, Vivian Zhai, Liangze Li, Rita Singh, and Bhiksha Raj. 2023a. Token prediction as implicit classification to identify LLM-generated text. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, pages 13112–13120. https://doi.org /… ↗
  13. Chern, I., Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, Pengfei Liu, et al. 2023. FacTool: Factuality detection in generative AI–A tool augmented framework for multi-task and multi-domain scenarios. ArXiv preprint, abs/2307.13528. find our card
  14. Chotikakamthorn, Nopporn. 1998. Electronic document data hiding technique using inter-character space. In IEEE. find
  15. APCCAS 1998. 1998 IEEE Asia-Pacific Conference on Circuits and Systems. Microelectronics and Integrating Systems. Proceedings (Cat. No. 98EX242), pages 419–422. https://doi.org/10.1109/APCCAS.1998.743799 Chowdhery, Aakanksha, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts,… ↗
  16. Christian, Jon. 2023. CNET secretly used AI on articles that didn’t disclose that fact, staff say. Futurism, January. https://futurism.com/cnet-ai -articles-label Clark, Elizabeth, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, and Noah A. Smith. 2021. All that’s ‘human’ is not gold:… ↗
  17. Dai, Damai, Yutao Sun, Li Dong, Yaru Hao, Shuming Ma, Zhifang Sui, and Furu Wei. 2023. Why can GPT learn in-context? Language models implicitly perform gradient descent as meta-optimizers. pages In ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models. https://doi.org /… ↗ our card
  18. Desaire, Heather, Aleesa E. Chua, Madeline Isom, Romana Jarosova, and David Hua. 2023. ChatGPT or academic scientist? Distinguishing authorship with over 99% accuracy using off-the-shelf machine learning tools. CoRR, abs/2303.16352. https://doi.org/10.1016/j .xcrp.2023.101426, PubMed: 37426542 Devli… — [doi:10.1016/j](https://doi.org/10.1016/j) find
  19. Dhaini, Mahdi, Wessel Poelman, and Ege Erdogan. 2023. Detecting ChatGPT: A survey of the state of detecting ChatGPT-generated text. CoRR, abs/2309.07689. https://doi.org/10.48550/ARXIV.2309.07689 Dong, Qingxiu, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang… ↗
  20. Dou, Yao, Maxwell Forbes, Rik Koncel-Kedziorski, Noah A. Smith, and Yejin Choi. 2022. Is GPT-3 text indistinguishable from human text? Scarecrow: A framework for scrutinizing machine text. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape… find
  21. Epstein, Ziv, Aaron Hertzmann; Investigators of Human Creativity; Memo Akten, Hany Farid, Jessica Fjeld, Morgan R. Frank, Matthew Groh, Laura Herman, Neil Leach, et al. 2023. Art and the science of generative AI. Science, 380(6650):1110–1111. https://doi.org/10.1126/science.adh4451, PubMed: 3731919… ↗ our card
  22. Fellbaum, Christiane. 1998. WordNet: An electronic lexical database. MIT Press. https://doi.org/10.7551/mitpress/7287.001.0001 Gade, Krishna, Sahin Geyik, Krishnaram Kenthapadi, Varun Mithal, and Ankur Taly. 2020. Explainable AI in industry: Practical challenges and lessons learned. In Companion Pr… — [doi:10.7551/mitpress](https://doi.org/10.7551/mitpress) ↗
  23. Gambini, Margherita, Tiziano Fagni, Fabrizio Falchi, and Maurizio Tesconi. 2022. On pushing DeepFake tweet detection capabilities to the limits. In Proceedings of the 14th ACM Web Science Conference 2022, pages 154–163. https://doi.org/10.1145/3501247.3531560 Gao, Chujie, Dongping Chen, Qihui Zhang… — [doi:10.1145/3501247.3531560](https://doi.org/10.1145/3501247.3531560) ↗
  24. Gao, Ji, Jack Lanchantin, Mary Lou Soffa, and Yanjun Qi. 2018. Black-box generation of adversarial text sequences to evade deep learning classifiers. In 2018 IEEE Security and Privacy Workshops (SPW), pages 50–56. https://doi.org/10.1109/SPW.2018.00016 Gao, Luyu, Zhuyun Dai, Panupong Pasupat, Antho… ↗ our card
  25. Giorgi, Salvatore, David M. Markowitz, Nikita Soni, Vasudha Varadarajan, Siddharth Mangalik, and H. Andrew Schwartz. 2023. “I slept like a baby”: Using human traits to characterize deceptive ChatGPT and human text. In Proceedings of the IACT - The 1st International Workshop on Implicit Author Charac… find
  26. Giorgi, Salvatore, Lyle Ungar, and H. Andrew Schwartz. 2021. Characterizing social spambots by their human traits. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5148–5158. https://doi.org/10.18653/v1/2021.findings-acl.457 Goodfellow, Ian, Jean Pouget-Abadie, M… ↗
  27. Guo, Biyang, Xin Zhang, Ziyuan Wang, Minqi Jiang, Jinran Nie, Yuxuan Ding, Jianwei Yue, and Yupeng Wu. 2023. How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection. ArXiv preprint, abs/2301.07597. Guo, Mandy, Zihang Dai, Denny Vrandečić, and Rami Al-Rfou. 2020. Wiki-40… find our card
  28. Guo, Zhen and Shangdi Yu. 2023. AuthentiGPT: Detecting machine-generated text via black-box language models denoising. CoRR, abs/2311.07700. https://doi.org/10 .48550/ARXIV.2311.07700 Hamed, Ahmed Abdeen and Xindong Wu. 2023. Improving detection of ChatGPT-generated fake science using real publicati… find
  29. He, Jianfei, Shichao Sun, Xiaohua Jia, and Wenjie Li. 2023a. Empirical analysis of beam search curse and search errors with model errors in neural machine translation. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 91–101. find
  30. He, Xinlei, Xinyue Shen, Zeyuan Chen, Michael Backes, and Yang Zhang. 2023b. MGTBench: Benchmarking machine-generated text detection. ArXiv preprint, abs/2303.14822. — [arXiv:2303.14822](https://arxiv.org/abs/2303.14822) find
  31. He, Zhiwei, Binglin Zhou, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, and Rui Wang. 2024. Can watermarks survive translation? On the cross-lingual consistency of text watermark for large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computatio… find
  32. Holtzman, Ari, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text degeneration. In 8th International Conference on Learning Representations, ICLR 2020, OpenReview.net. find
  33. Horne, Benjamin and Sibel Adali. 2017. This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news. In Proceedings of the International AAAI Conference on Web and Social Media, volume 11, pages 759–766. https://doi.org/10.1609/i… — [doi:10.1609/icwsm.v11i1.14976](https://doi.org/10.1609/icwsm.v11i1.14976) find
  34. Ibrahim, Hazem, Fengyuan Liu, Rohail Asim, Balaraju Battu, Sidahmed Benabderrahmane, Bashar Alhafni, Wifag Adnan, Tuka Alhanai, Bedoor K. AlShebli, Riyadh Baghdadi, et al. 2023. Perception, performance, and detectability of conversational artificial intelligence across 32 university courses. CoRR, a… — [doi:10.48550/arxiv.2305.13934](https://doi.org/10.48550/arxiv.2305.13934) find
  35. Jawahar, Ganesh, Muhammad Abdul-Mageed, and Laks Lakshmanan, V. S. 2020. Automatic detection of machine generated text: A critical survey. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2296–2309. International Committee on Computational Linguistics. https://… find our card
  36. Kang, Dongyeop, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, and Roy Schwartz. 2018. A dataset of peer reviews (PeerRead): Collection, insights and NLP applications. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Com… find our card
  37. Kirchenbauer, John, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, and Tom Goldstein. 2023b. On the reliability of watermarks for large language models. CoRR, abs/2306.04634. https://doi.org/10.48550/arXiv.2306.04634 Kitchenham, Ba… ↗
  38. Koike, Ryuto, Masahiro Kaneko, and Naoaki Okazaki. 2023a. How you prompt matters! Even task-oriented constraints in instructions affect LLM-generated text detection. CoRR, abs/2311.08369. https://doi.org/10.48550/ARXIV.2311.08369, https://doi.org/10.18653/v1/2024.findings-emnlp.841 Koike, Ryuto, M… ↗
  39. Kojima, Takeshi, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In NeurIPS. find our card
  40. Krishna, Kalpesh, Yixiao Song, Marzena Karpinska, John Wieting, and Mohit Iyyer. 2023. Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense. ArXiv preprint, abs/2303.13408. find our card
  41. Kuditipudi, Rohith, John Thickstun, Tatsunori Hashimoto, and Percy Liang. 2023. Robust distortion-free watermarks for language models. CoRR, abs/2307.15593. https://doi.org/10.48550/ARXIV.2307.15593 Kuditipudi, Rohith, John Thickstun, Tatsunori Hashimoto, and Percy Liang. 2024. Robust distortion-fr… ↗
  42. Kulkarni, Pranav, Ziqing Ji, Yan Xu, Marko Neskovic, and Kevin Nolan. 2023. Exploring semantic perturbations on Grover. CoRR, abs/2302.00509. https://doi.org/10.48550/ARXIV.2302.00509 Kumarage, Tharindu, Amrita Bhattacharjee, Djordje Padejski, Kristy Roschke, Dan Gillmor, Scott W. Ruston, Huan Liu,… ↗
  43. Lee, Bruce W., Yoo Sung Jang, and Jason Hyung-Jong Lee. 2021. Pushing on text readability assessment: A transformer meets handcrafted linguistic features. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event, pages 10669–10686. https://… find
  44. Li, Yafu, Qintong Li, Leyang Cui, Wei Bi, Longyue Wang, Linyi Yang, Shuming Shi, and Yue Zhang. 2023c. Deepfake text detection in the wild. CoRR, abs/2305.13242. https://doi.org/10.48550/arXiv.2305.13242 Liang, Gongbo, Jesus Guerrero, and Izzat Alsmadi. 2023. Mutation-based adversarial attacks on n… — [doi:10.48550/arxiv.2305.13242](https://doi.org/10.48550/arxiv.2305.13242) ↗
  45. Liang, Weixin, Mert Yuksekgonul, Yining Mao, Eric Wu, and James Zou. 2023a. GPT detectors are biased against non-native English writers. In ICLR 2023 Workshop on Trustworthy and Reliable Large-Scale Machine Learning Models. https://doi.org/10.1016/j.patter.2023.100779, PubMed: 37521038 Liang, Yaobo… ↗ our card
  46. Lin, Stephanie, Jacob Hilton, and Owain Evans. 2022. TruthfulQA: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252. https://doi.org/10.18653/v1/2022 .acl-long.229 Littman, J… ↗ our card
  47. Liu, Aiwei, Leyi Pan, Xuming Hu, Shu’ang Li, Lijie Wen, Irwin King, and Philip S. Yu. 2023a. A private watermark for large language models. ArXiv preprint, abs/2307.16230. — [arXiv:2307.16230](https://arxiv.org/abs/2307.16230) find
  48. Liu, Aiwei, Leyi Pan, Xuming Hu, Shiao Meng, and Lijie Wen. 2023b. A semantic invariant robust watermark for large language models. CoRR, abs/2310.06356. https://doi.org/10.48550/ARXIV.2310.06356 Liu, Aiwei, Leyi Pan, Yijian Lu, Jingjing Li, Xuming Hu, Lijie Wen, Irwin King, and Philip S. Yu. 2023c… ↗ our card
  49. Liu, Yinhan, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692. find
  50. Liu, Yikang, Ziyin Zhang, Wanyang Zhang, Shisen Yue, Xiaojing Zhao, Xinyuan Cheng, Yiwen Zhang, and Hai Hu. 2023d. ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models. ArXiv preprint, abs/2304.07666. — [arXiv:2304.07666](https://arxiv.org/abs/2304.07666) find
  51. Liu, Zeyan, Zijun Yao, Fengjun Li, and Bo Luo. 2023e. Check me if you can: Detecting ChatGPT-generated academic writing using CheckGPT. ArXiv preprint, abs/2306.05524. — [arXiv:2306.05524](https://arxiv.org/abs/2306.05524) find
  52. Lowerre, Bruce P. and B. Raj Reddy. 1976. Harpy, a connected speech recognition system. The Journal of the Acoustical Society of America, 59(S1):S97–S97. https://doi.org/10.1121/1.2003013 Lu, Ning, Shengcai Liu, Rui He, and Ke Tang. 2023. Large language models can be guided to evade AI-generated te… — [doi:10.1121/1.2003013](https://doi.org/10.1121/1.2003013) ↗
  53. Lu, Yaojie, Qing Liu, Dai Dai, Xinyan Xiao, Hongyu Lin, Xianpei Han, Le Sun, and Hua Wu. 2022. Unified structure generation for universal information extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, pages 5755–5… find
  54. Ma, Yongqiang, Jiawei Liu, Fan Yi, Qikai Cheng, Yong Huang, Wei Lu, and Xiaozhong Liu. 2023. AI vs. human–differentiation analysis of scientific content generation. arXiv, https://arxiv.org/abs/2301 .10416 Macko, Dominik, Róbert Móro, Adaku Uchendu, Jason Samuel Lucas, Michiharu Yamashita, Matús… ↗
  55. Mindner, Lorenz, Tim Schlippe, and Kristina Schaaff. 2023. Classification of human- and AI-generated texts: Investigating features for ChatGPT. CoRR, abs/2308.05341. https://doi.org/10.48550/ARXIV.2308.05341, https://doi.org/10.1007/978-981-99-7947-9 12 Mirsky, Yisroel, Ambra Demontis, Jaidip Kota… ↗ our card
  56. Moosavi, Nafise Sadat, Andreas Rücklé, Dan Roth, and Iryna Gurevych. 2021. SciGen: A dataset for reasoning-aware text generation from scientific tables. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). find
  57. Morris, John X., Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi. 2020. TextAttack: A framework for adversarial attacks, data augmentation, and adversarial training in NLP. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations… find our card
  58. Murtaza, Ghulam, Liyana Shuib, Ainuddin Wahid Abdul Wahab, Ghulam Mujtaba, Ghulam Mujtaba, Henry Friday Nweke, Mohammed Ali Al-garadi, Fariha Zulfiqar, Ghulam Raza, and Nor Aniza Azmi. 2020. Deep learning-based breast cancer classification through medical imaging modalities: State of the art and res… find
  59. Nguyen-Son, Hoang-Quoc, Minh-Son Dao, and Koji Zettsu. 2024. SimLLM: Detecting sentences generated by large language models using similarity between the generation and its re-generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, pages 2234… find
  60. OpenAI. 2023. GPT-4 technical report. CoRR, abs/2303.08774. https://doi.org/10.48550/arXiv.2303.08774 Orenstrakh, Michael Sheinman, Oscar Karnalim, Carlos Anibal Suarez, and Michael Liut. 2023. Detecting LLM-generated text in computing education: A comparative study for ChatGPT cases. ArXiv preprin… ↗ our card
  61. Ouyang, Long, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback, 2022. ArXiv preprint, abs/2203.02155. find
  62. Pagnoni, Artidoro, Martin Graciarena, and Yulia Tsvetkov. 2022. Threat scenarios and best practices to detect neural fake news. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1233–1249. find
  63. Peng, Xinlin, Ying Zhou, Ben He, Le Sun, and Yingfei Sun. 2024. Hidding the ghostwriters: An adversarial evaluation of AI-generated student essay detection. CoRR, abs/2402.00412. https://doi.org/10.48550/ARXIV.2402.00412 Piccolo, Stephen R., Paul Denny, Andrew Luxton-Reilly, Samuel Payne, and Perry… ↗
  64. Por, L. Y., T. F. Ang, and B. Delina. 2008. WhiteSteg: A new scheme in information hiding using text steganography. WSEAS Transactions on Computers, 7(6):735–745. find
  65. Por, Lip Yee, KokSheik Wong, and Kok Onn Chee. 2012. UniSpaChi: A text-based data hiding method using Unicode space characters. Journal of Systems and Software, 85(5):1075–1082. https://doi.org/10.1016/J.JSS.2011.12.023 Porsdam Mann, Sebastian, Brian D Earp, Sven Nyholm, John Danaher, Nikolaj Mølle… ↗
  66. Raffel, Colin, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21:140:1–140:67. find
  67. Rajpurkar, Pranav, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392. https://doi.org/10.18653/v1/D16-1264 Ren, Shuhuai, Yihe… ↗ our card
  68. Sadasivan, Vinu Sankar, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, and Soheil Feizi. 2023. Can AI-generated text be reliably detected? ArXiv preprint, abs/2303.11156. find our card
  69. Saeed, Waddah and Christian Omlin. 2023. Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities. Knowledge-Based Systems, 263:110273. https://doi.org/10.1016/j.knosys.2023.110273 Sarvazyan, Areg Mikael, José Ángel González, Paolo Rosso, and Marc Franco-Salv… ↗
  70. Schneider, Sinclair, Florian Steuber, Joao A. G. Schneider, and Gabi Dreo Rodosek. 2023. How well can machine-generated texts be identified and can language models be trained to avoid identification? CoRR, abs/2310.16992. https://doi.org/10.48550/ARXIV.2310.16992, https://doi.org/10.24251/HICSS .20… — [doi:10.48550/arxiv.2310.16992](https://doi.org/10.48550/arxiv.2310.16992) ↗
  71. Schuster, Tal, Roei Schuster, Darsh J. Shah, and Regina Barzilay. 2020. The limitations of stylometry for detecting machine-generated fake news. Computational Linguistics, 46(2):499–510. https://doi.org/10.1162/coli a 00380 Seals, S. M. and Valerie L. Shalin. 2023. Long-form analogies generated by C… ↗
  72. Shevlane, Toby, Sebastian Farquhar, Ben Garfinkel, Mary Phuong, Jess Whittlestone, Jade Leung, Daniel Kokotajlo, Nahema Marchal, Markus Anderljung, Noam Kolt, Lewis Ho, Divya Siddarth, Shahar Avin, Will Hawkins, Been Kim, Iason Gabriel, Vijay Bolina, Jack Clark, Yoshua Bengio, Paul F. Christiano, an… find
  73. Shumailov, Ilia, Zakhar Shumaylov, Yiren Zhao, Nicolas Papernot, Ross Anderson, and Yarin Gal. 2024. AI models collapse when trained on recursively generated data. Nature, 631(8022):755–759. https://doi.org/10.1038/s41586-024-07566-y PubMed: 39048682 Sokolova, Marina, Nathalie Japkowicz, and Stan S… ↗
  74. Soni, Mayank and Vincent Wade. 2023. Comparing abstractive summaries generated by ChatGPT to real summaries through blinded reviewers and text classification algorithms. CoRR, abs/2303.17650. https://doi.org/10.48550/ARXIV.2303.17650 Stiff, Harald and Fredrik Johansson. 2022. Detecting computer-gen… ↗ our card
  75. Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, pages 3104–3112. find
  76. Tang, Ruixiang, Yu-Neng Chuang, and Xia Hu. 2023. The science of detecting LLM-generated texts. CoRR, abs/2303.07205. https://doi.org/10.48550/arXiv.2303.07205 Tang, Ruixiang, Yu-Neng Chuang, and Xia Hu. 2024. The science of detecting LLM-generated text. Communications of the ACM, 67(4):50–59. http… ↗
  77. Uchendu, Adaku, Thai Le, and Dongwon Lee. 2023a. Attribution and obfuscation of neural text authorship: A data mining perspective. SIGKDD Explorations Newsletter, 25(1):1–18. https://doi.org/10.1145/3606274.3606276 — [doi:10.1145/3606274.3606276](https://doi.org/10.1145/3606274.3606276) ↗
  78. Uchendu, Adaku, Thai Le, and Dongwon Lee. 2023b. TOPROBERTA: Topology-aware authorship attribution of deepfake texts. CoRR, abs/2309.12934. https://doi.org/10.48550/ARXIV .2309.12934, https://doi.org/10 .3233/FAIA240647 Uchendu, Adaku, Thai Le, Kai Shu, and Dongwon Lee. 2020. Authorship attribution… ↗ our card
  79. Venkatraman, Saranya, He He, and David Reitter. 2023. How do decoding algorithms distribute information in dialogue responses? In Findings of the Association for Computational Linguistics: EACL 2023, pages 923–932. https://doi.org/10.18653/v1/2023.findings -eacl.70 Venkatraman, Saranya, Adaku Uchen… ↗
  80. Walters, William H. 2023. The effectiveness of software designed to detect AI-generated writing: A comparison of 16 AI text detectors. Open Information Science, 7(1):20220158. https://doi.org/10.1515/opis-2022-0158 Wang, Alex, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bo… ↗
  81. Wang, Zecong, Jiaxi Cheng, Chen Cui, and Chenhao Yu. 2023c. Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT. CoRR, abs/2306.07401. https://doi.org/10.48550/ARXIV.2306.07401 Weber-Wulff, Debora, Alla Anohina-Naumeca, Sonja Bjelobaba, Tomáš Foltỳnek, Jean Guerrero-D… ↗
  82. Weidinger, Laura, John Mellor, Maribeth Rauh, Conor Griffin, Jonathan Uesato, Po-Sen Huang, Myra Cheng, Mia Glaese, Borja Balle, Atoosa Kasirzadeh, et al. 2021. Ethical and social risks of harm from language models (2021). ArXiv preprint, abs/2112.04359. find our card
  83. Weng, Luoxuan, Minfeng Zhu, Kam Kwai Wong, Shi Liu, Jiashun Sun, Hang Zhu, Dongming Han, and Wei Chen. 2023. Towards an understanding and explanation for mixed-initiative artificial scientific text detection. ArXiv preprint, abs/2304.05011. — [arXiv:2304.05011](https://arxiv.org/abs/2304.05011) find
  84. Wikipedia. 2023. Large language models and copyright. https://en.wikipedia.org/wiki/Wikipedia:Large language models and copyright Winstein, Keith. 1998. Lexical steganography through adaptive modulation of the word choice hash. Unpublished. http://www.imsa.edu/~keithw/tlex ↗
  85. Wolff, Max. 2020. Attacking neural text detectors. CoRR, abs/2002.11768. — [arXiv:2002.11768](https://arxiv.org/abs/2002.11768) find
  86. Wu, Junchao, Runzhe Zhan, Derek F. Wong, Shu Yang, Xuebo Liu, Lidia S. Chao, and Min Zhang. 2024a. Who wrote this? The key to zero-shot LLM-generated text detection is GECScore. CoRR, abs/2405.04286. https://doi.org/10.48550/ARXIV.2405.04286 Wu, Junchao, Runzhe Zhan, Derek F. Wong, Shu Yang, Xinyi… ↗
  87. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2113–2133. https://doi.org/10.18653/v1/2023.findings -emnlp.139 Xiang, Lingyun, Yan Li, Wei Hao, Peng Yang, and Xiaobo Shen. 2018. Reversible natural language watermarking using synonym substitution and arithmetic codin… — [doi:10.18653/v1/2023.findings](https://doi.org/10.18653/v1/2023.findings) ↗
  88. Yan, Duanli, Michael Fauss, Jiangang Hao, and Wenju Cui. 2023. Detection of AI-generated essays in writing assessment. Psychological Testing and Assessment Modeling, 65(2):125–144. find
  89. Yan, Yuanmeng, Rumei Li, Sirui Wang, Fuzheng Zhang, Wei Wu, and Weiran Xu. 2021. ConSERT: A contrastive framework for self-supervised sentence representation transfer. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conferen… find our card
  90. Yang, Zhilin, Zihang Dai, Yiming Yang, Jaime G. Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. 2019. XLNet: Generalized autoregressive pretraining for language understanding. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, N… find our card
  91. Yao, Shunyu, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models, May 2023. ArXiv preprint, abs/2305.10601. find
  92. Yasunaga, Michihiro and Percy Liang. 2021. Break-it-fix-it: Unsupervised learning for program repair. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, volume 139 of Proceedings of Machine Learning Research, pages 11941–11952. find
  93. Yoo, KiYoon, Wonhyuk Ahn, Jiho Jang, and Nojun Kwak. 2023. Robust multi-bit natural language watermarking through invariant features. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, pages 2092–2115. https://doi.org/10.1865… find
  94. Zellers, Rowan, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019a. HellaSwag: Can a machine really finish your sentence? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4791–4800. https://doi.org/10.18653/v1/P19-1472 ↗
  95. Zellers, Rowan, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019b. Defending against neural fake news. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, pages 9051–90… find our card
  96. Zhang, Ruisi, Shehzeen Samarah Hussain, Paarth Neekhara, and Farinaz Koushanfar. 2023a. REMARK-LLM: A robust and efficient watermarking framework for generative large language models. CoRR, abs/2310.12362. https://doi.org/10.48550/ARXIV.2310.12362 Zhang, Yue, Yafu Li, Leyang Cui, Deng Cai, Lemao Li… ↗ our card
  97. Zhang, Yi-Fan, Zhang Zhang, Liang Wang, Tieniu Tan, and Rong Jin. 2023c. Assaying on the robustness of zero-shot machine-generated text detectors. CoRR, abs/2312.12918. https://doi.org/10.48550/ARXIV.2312.12918 Zhao, Zihao, Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. 2021. Calibrate before… ↗ our card
  98. Zhong, Wanjun, Duyu Tang, Zenan Xu, Ruize Wang, Nan Duan, Ming Zhou, Jiahai Wang, and Jian Yin. 2020. Neural deepfake detection with factual structure of text. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2461–2470. https://doi.org/10.18653… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2025-survey-llm-generated-text-detection/