Li et al. (2025f) introduced a general statistical framework for watermark detection in Large Language Models based on hypothesis testing using a pivotal statistic, enabling the rigorous evaluation of detection efficiency through class-dependent efficiency (the rate of Type II error decay).

Authors

• Person: Not available Organization: arXiv
  A Survey on the Theory and Mechanism of Large Language Models

Sources

• A Survey on the Theory and Mechanism of Large Language Models arxiv.org arXiv via serper

Referenced by nodes (1)

• Large Language Models concept