paperAugust 2026Unreviewed

Optimal Watermark Localization in Mixed-Source Large Language Model Texts

José H. Blanchet, T. Cai, Xiang Li, Hao Liu, Qi Long, Weijie J. Su

Abstract

Watermarking provides a principled way to authenticate text generated by large language models (LLMs). In practice, however, the final text may be mixed-source, with watermark evidence surviving at only a subset of token positions after rewriting, insertion, deletion, or paraphrasing. Although prior work has studied global detection of watermark signals, when such signals can be localized remains unclear. We formulate watermark localization as a token-level multiple-testing problem based on pivo

Cite

@misc{blanchet2026optimal,
  title = {{Optimal Watermark Localization in Mixed-Source Large Language Model Texts}},
  author = {José H. Blanchet and T. Cai and Xiang Li and Hao Liu and Qi Long and Weijie J. Su},
  year = {2026},
  month = aug,
  eprint = {2608.14906},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/9d38112c12c8aed8b21ee18522eed2e3b185a8ac}
}