← 研踪 PaperTrailarXiv:2611.19305 · v1
Fundamental Limits of Statistical Watermarking for LLMs with Fixed and Optimizable Common Randomness
首次提交 2026-11-14 18:05
版本更新 2026-11-14 18:05
雷达观测 2026-11-17 12:06
摘要
Watermarking has emerged as an important technique for distinguishing AI-generated text from human-written text. However, most existing work is primarily empirical, relies on ad hoc watermarking designs, and lacks a fundamental understanding of the performance limits. In this paper, we propose a unified theoretical framework for statistical watermarking of large language models (LLMs), casting the problem as an independence test between generated text and common randomness and jointly designing the watermarking embedder and the detector. Our objective is to maximize detection power while controlling the worst-case false positive rate (FPR) and limiting distortion to text quality. A central focus of our framework is the design of the common randomness, which plays a critical role in both watermark embedding and detection. We characterize the fundamental limits of statistical watermarking under both fixed and optimizable common randomness. Our results show that optimizing the common randomness does not improve the fundamental limits: the best achievable performance is the same as that with fixed common randomness. Nevertheless, common randomness design remains highly important because it can substantially simplify detector design. In particular, with optimizable common randomness, a fixed, deterministic, and model-agnostic detector can achieve optimal performance. We further study a practical setting with fixed uniform common randomness and a fixed deterministic detector, and characterize its performance gap relative to the optimizable case, thereby demonstrating the practical value of optimizable common randomness.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-14 18:05 · 最新观测版本
Fundamental Limits of Statistical Watermarking for LLMs with Fixed and Optimizable Common Randomness
Watermarking has emerged as an important technique for distinguishing AI-generated text from human-written text. However, most existing work is primarily empirical, relies on ad hoc watermarking designs, and lacks a fundamental understanding of the performance limits. In this paper, we propose a unified theoretical framework for statistical watermarking of large language models (LLMs), casting the problem as an independence test between generated text and common randomness and jointly designing the watermarking embedder and the detector. Our objective is to maximize detection power while controlling the worst-case false positive rate (FPR) and limiting distortion to text quality. A central focus of our framework is the design of the common randomness, which plays a critical role in both watermark embedding and detection. We characterize the fundamental limits of statistical watermarking under both fixed and optimizable common randomness. Our results show that optimizing the common randomness does not improve the fundamental limits: the best achievable performance is the same as that with fixed common randomness. Nevertheless, common randomness design remains highly important because it can substantially simplify detector design. In particular, with optimizable common randomness, a fixed, deterministic, and model-agnostic detector can achieve optimal performance. We further study a practical setting with fixed uniform common randomness and a fixed deterministic detector, and characterize its performance gap relative to the optimizable case, thereby demonstrating the practical value of optimizable common randomness.
查看此版本解读 →查看此版本原文 ↗