Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
Tom Sander, Pierre Fernandez, Itai Gat +11
We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked…
cs.CR2026
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
Tom Sander, Hongyan Chang, Tomáš Souček +10
We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity,…