5 citations · 19 across the 10 of their papers we have counts for
4 papers · 1 filter
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
Zhengmian Hu, Heng Huang
Large language models are probabilistic models, and the process of generating content is essentially sampling from the output distribution of the language model. Existing watermark…
Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions
Yihan Wu, Ruibo Chen, Zhengmian Hu +4
Language model (LM) watermarking techniques inject a statistical signal into LM-generated content by substituting the random sampling process with pseudo-random sampling, using wat…
Unbiased Watermark for Large Language Models
Zhengmian Hu, Lichang Chen, Xidong Wu +3
The recent advancements in large language models (LLMs) have sparked a growing apprehension regarding the potential misuse. One approach to mitigating this risk is to incorporate w…
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
Yihan Wu, Zhengmian Hu, Junfeng Guo +2
Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge i…