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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xiang, Ruan, Feng, Wang, Huiyuan, Long, Qi, Su, Weijie J.
Format:	Preprint
Published:	2024
Subjects:	Statistics Theory Computation and Language Cryptography and Security Machine Learning 62C05 (Primary), 62F03 (Secondary)
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2404.01245