统一了大模型水印方法，揭示了质量、多样性与可检测性的权衡关系。
A Unified Framework for LLM Watermarks
- 从约束优化视角统一现有水印算法，揭示其内在机制。
- 不同约束下设计的水印方案均显著提升可检测性。
- 适用于需要定制化水印的场景，如注重生成质量时。
大模型水印可通过在生成文本中插入可检测信号实现内容溯源。现有水印方法设计各异，多采用自下而上的方式，缺乏通用且有理论基础的框架。本文表明，多数现有水印方案均可由一个统一的约束优化问题推导得出。该框架不仅整合了已有方法，还显式揭示了每种方法所优化的约束条件。特别地，它揭示了一个被忽视的质量-多样性-可检测性三者权衡关系。同时，该框架为定制新型水印方案提供了理论指导，例如可直接以困惑度（perplexity）作为质量代理指标，并推导出针对该约束最优的新方案。实验验证表明，基于特定约束推导的水印方案，在对应约束下始终具备最强的可检测性。
原文摘要 · Abstract (English)
LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up approach. Crucially, there is no general and principled formulation for LLM watermarking. In this work, we show that most existing and widely used watermarking schemes can in fact be derived from a principled constrained optimization problem. Our formulation unifies existing watermarking methods and explicitly reveals the constraints that each method optimizes. In particular, it highlights an understudied quality-diversity-power trade-off. At the same time, our framework also provides a principled approach for designing novel watermarking schemes tailored to specific requirements. For instance, it allows us to directly use perplexity as a proxy for quality, and derive new schemes that are optimal with respect to this constraint. Our experimental evaluation validates our framework: watermarking schemes derived from a given constraint consistently maximize detection power with respect to that constraint.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。