Awesome License-MIT PRs-Welcome last-commit

The powerful ability of large language models (LLMs) to understand, follow, and generate complex languages has enabled LLM-generated texts to flood many areas of our daily lives at an incredible rate, with potentially negative impacts and risks on society and academia. As LLMs continue to expand, how can we detect LLM-generated texts to help minimize the threat posed by the misuse of LLMs?

1 Junchao Wu, 1 Shu Yang, 1 Runzhe Zhan, 1 2 Yulin Yuan, 1 Derek Fai Wong, 1 Lidia Sam Chao

1 University of Macau, 2 Peking University

• [2024年09月26日] ✨ Our benchmark paper is accepted by NeurIPS 2024 D&B track. We released DetectRL, a benchmark for real-world LLM-generated text detection, provide real utility to researchers on the topic and practitioners looking for consistent evaluation methods. Please refer to arXiv: DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios and Github Repo DetectRL for details.
• [2023年10月24日] Our survey paper is now available on arXiv: A Survey on LLM-generated Text Detection: Necessity, Methods, and Future Directions .
• [2023年05月01日] : We began to explore the topic of LLM-generated Text Detection.

• Awesome LLM-generated Text Detection
  • 📢 News
  • � Table of Contents
  • 📃 Papers
    • Overview
    • Datasets
      • Benchmarks
      • Potential Datasets
    • Detector
      • Watermark Technology
      • Zero-shot Methods
      • Fine-tuning LMs Methods
      • Adversarial Learning Methods
      • LLMs as Detector
    • Related Works
      • Other Surveys
  • 🚩 Citation
  • Contributing

A survey and reflection on the latest research breakthroughs in LLM-generated Text detection, including data, detectors, metrics, current issues and future directions. Please refer to our article/paper for more details.

If our research helps you, please kindly cite our paper.

@article{wu2023survey,
 title={A Survey on LLM-gernerated Text Detection: Necessity, Methods, and Future Directions}, 
 author={Junchao Wu and Shu Yang and Runzhe Zhan and Yulin Yuan and Derek F. Wong and Lidia S. Chao},
 journal = {CoRR},
 volume = {abs/2310.14724},
 year = {2023},
 url = {https://arxiv.org/abs/2310.14724},
 eprinttype = {arXiv},
 eprint = {2310.14724},

Contributions are welcome! If you have any ideas, suggestions, or bug reports, please open an issue or submit a pull request. We appreciate your contributions to making LLM-generated Text Detection work even better.