A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules

Published in The Annals of Statistics, 2025

Recommended citation: Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, and Weijie J. Su. "A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules." The Annals of Statistics 53(1) (2025), 322–351. Invited for presentation at the Annals of Statistics discussion session, Joint Statistical Meetings 2025. https://doi.org/10.1214/24-AOS2468