Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang

AAAI 2025 pp. 25002-25009

doi:10.1609/AAAI.V39I23.34684 /aaai/2025/panaitesculiess2025aaai-watermarking/

AAAI Semantic Scholar

Cite

Text

Panaitescu-Liess et al. "Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I23.34684

Markdown

[Panaitescu-Liess et al. "Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/panaitesculiess2025aaai-watermarking/) doi:10.1609/AAAI.V39I23.34684

BibTeX

@inproceedings{panaitesculiess2025aaai-watermarking,
  title     = {{Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?}},
  author    = {Panaitescu-Liess, Michael-Andrei and Che, Zora and An, Bang and Xu, Yuancheng and Pathmanathan, Pankayaraj and Chakraborty, Souradip and Zhu, Sicheng and Goldstein, Tom and Huang, Furong},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {25002-25009},
  doi       = {10.1609/AAAI.V39I23.34684},
  url       = {https://mlanthology.org/aaai/2025/panaitesculiess2025aaai-watermarking/}
}