OpenStamp: A Watermark for Open-Source Language Models

Abstract

With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to LLMs and distinguishing it from human-written content. A prominent class of techniques embeds subtle but detectable signals in generated text by modifying token sampling probabilities. However, such methods are unsuitable for open-source models, where users have white-box access and can easily disable watermarking during inference. In this work, we

Categories

@misc{bakshi2026openstamp,
  title = {{OpenStamp: A Watermark for Open-Source Language Models}},
  author = {Miroojin Bakshi and Saksham Rastogi and Danish Pruthi},
  year = {2026},
  month = aug,
  eprint = {2608.27899},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/4e7740b43503b5154dae21b1aae91874490a9ac4}
}