A Text Watermark for Large Language Models

Abstract

Proposes a watermarking framework for LLM-generated text that embeds a statistically detectable signal without significantly affecting output quality.

Categories

Framework mappings

@inproceedings{kirchenbauer2023text,
  title = {{A Text Watermark for Large Language Models}},
  author = {John Kirchenbauer and Jonas Geiping and Yuxin Wen and Jonathan Katz and Ian Miers and Tom Goldstein},
  year = {2023},
  month = jun,
  booktitle = {ICML 2023},
  eprint = {2301.10226},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2301.10226}
}