English

Multi-Bit Distortion-Free Watermarking for Large Language Models

Computation and Language 2024-02-27 v1 Machine Learning

Abstract

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the watermark to adversarial detection. More recently, distortion-free watermarking methods were proposed that require a secret key to detect the watermark. The prior methods generally embed zero-bit watermarks that do not provide additional information beyond tagging a text as being AI-generated. We extend an existing zero-bit distortion-free watermarking method by embedding multiple bits of meta-information as part of the watermark. We also develop a computationally efficient decoder that extracts the embedded information from the watermark with low bit error rate.

Keywords

Cite

@article{arxiv.2402.16578,
  title  = {Multi-Bit Distortion-Free Watermarking for Large Language Models},
  author = {Massieh Kordi Boroujeny and Ya Jiang and Kai Zeng and Brian Mark},
  journal= {arXiv preprint arXiv:2402.16578},
  year   = {2024}
}
R2 v1 2026-06-28T15:00:19.303Z