6 citations · 34 across the 24 of their papers we have counts for
Showing 2024 · cs.CRShow all
2 papers · 2 filters
cs.CR2024
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…
cs.CR2024★ 1 cited
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…