Towards Better Statistical Understanding of Watermarking LLMs

arXiv:2403.13027v1 Announce Type: cross
Abstract: In this paper, we study the problem of watermarking large language models (LLMs). We consider the trade-off between model distortion and detection ability and formulate it as a constrained optimization problem based on the green-red algorithm of Kirchenbauer et al. (2023a). We show that the optimal solution to the optimization problem enjoys a nice analytical property which provides a better understanding and inspires the algorithm design for the watermarking process. We develop an online dual …

abstract algorithm arxiv cs.cr cs.it cs.lg detection green language language models large language large language models llms math.it optimization paper show solution statistical stat.ml study trade trade-off type understanding watermarking