activity
20142026
most citedThe generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime

88 citations · 333 across the 26 of their papers we have counts for

collaborators
Showing 2024 · math.STShow all

1 paper · 2 filters

math.ST2024★ 17 cited

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

Xiang Li, Feng Ruan, Huiyuan Wang +2

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking,…