发表机构
Yunnan Key Laboratory of Statistical Modeling and Data Analysis; Yunnan University; School of Statistics and Management; Shanghai University of Finance and Economics（云南统计建模与数据分析重点实验室; 云南大学; 统计与管理学院; 上海财经大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究如何在大语言模型中高效检测水印，基于Rao-Blackwellized e过程开发在线检测框架，针对Gumbel-max水印实例化，能随时有效推理、递归更新证据，理论证明其有效性，模拟和实验验证了高效在线检测。
AI 中文摘要
随着大语言模型（LLMs）的广泛应用，区分人工智能生成文本和人类撰写内容的可靠高效机制变得至关重要。统计水印技术成为一种有前景的解决方案，但现有的大多数方法是固定范围程序，无法在流生成中有效提前停止。本文基于Rao-Blackwellized e过程开发了一个高效的在线水印检测框架，能进行随时有效的推理，实现递归令牌级证据更新且无需存储完整历史。具体针对Gumbel-max水印实例化该框架，将原始令牌级依赖测试问题简化为具有明确零分布的枢轴诱导顺序测试问题。理论上，证明了在任意可选停止下随时有效的第一类错误控制，并在水印下建立了正渐近对数增长，意味着所提出的停止规则具有一致性。在真实LLM生成文本上的模拟和实验证明了具有严格随时有效保证的高效在线检测。
英文摘要
As large language models (LLMs) are increasingly deployed, reliable and efficient mechanisms for distinguishing AI-generated text from human-written content have become essential. Statistical watermarking has emerged as a promising solution, yet most existing methods are typically fixed-horizon procedures, precluding valid early stopping in streaming generation. In this paper, we develop an efficient online watermark detection framework with anytime-valid inference based on Rao-Blackwellized e-processes, enabling recursive token-level evidence updates without storing the full history. In particular, we instantiate the framework for the Gumbel-max watermark and reduce the original token-level dependence testing problem to a pivot-induced sequential testing problem with an explicit null distribution. Theoretically, we prove anytime-valid Type I error control under arbitrary optional stopping and establish positive asymptotic log-growth under watermarking, implying consistency of the proposed stopping rules. Simulations and experiments on real LLM-generated text demonstrate efficient online detection with rigorous anytime-valid guarantees.
Comments25 pages, 3 figures
