A Unified Framework for LLM Watermarks

Thibaud Gloaguen, Robin Staab, Nikola Jovanović, Martin Vechev

Abstract

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.
BibTeX
@misc{gloaguen2026unified,
  author = {Thibaud Gloaguen and Robin Staab and Nikola Jovanović and Martin Vechev},
  title = {{A Unified Framework for LLM Watermarks}},
  year = {2026},
  eprint = {2602.06754},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.06754},
}

Loading related content...

Figure