AI-Generated Text Detection: Challenges and Future Directions
Author:
- 1 June 2023
- journal article
- review article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Asian Language Processing
- Vol. 33 (02)
Abstract
With the rapid development of large language models (LLMs), the quality of AI-generated context (AIGC) is rapidly improving, and the correctness and detection of generated content have become a global challenge. In this paper, we review the current methods of AIGC detector and introduce the definition, dataset and methods of AIGC detection, including the manual-based methods, rule-based methods, statistical learning-based methods, deep learning-based methods, knowledge enhancement-based methods and watermarking-based methods. However, these methods have very low recognition accuracy when facing the latest LLMs, such as ChatGPT and GPT-4. This paper also suggests that more work should be put into identifying AIGC quality in the future, such as whether there are logical errors, knowledge errors or data falsification, which may have more severe consequences and be more likely to be detected.Keywords
Funding Information
- National Natural Science Foundation of China (62076233, 62266036)
This publication has 19 references indexed in Scilit:
- FL-MGVN: Federated learning for anomaly detection using mixed gaussian variational self-encoding networkInformation Processing & Management, 2022
- The Robots Are Coming: Exploring the Implications of OpenAI Codex on Introductory Programming2022
- TweepFake: About detecting deepfake tweetsPLOS ONE, 2021
- Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural NetworkIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- CPM: A large-scale generative Chinese Pre-trained language modelAI Open, 2021
- Natural Language Processing2020
- E2E NLG Challenge: Neural Models vs. Templates2018
- Enriching Word Vectors with Subword InformationTransactions of the Association for Computational Linguistics, 2017
- Understanding bag-of-words model: a statistical frameworkInternational Journal of Machine Learning and Cybernetics, 2010
- Adversarial learning2005