LLM watermarking
New research proposes a linguistics-aware watermarking method for LLMs that embeds detectable signals into generated text without distorting output quality, advancing AI content authentication.
LLM watermarking
New research introduces ArcMark, a multi-bit watermarking method for LLMs using optimal transport theory to embed verifiable information in AI-generated text while preserving output quality.
LLM watermarking
Researchers introduce WaterMod, a modular token-rank partitioning approach that improves LLM watermarking by maintaining probability balance across model outputs, enhancing detection while preserving text quality.