A research implementation of statistical text watermarking for large language models using Plug and Play Language Models (PPLM). This system enables detectable watermark embedding through direct logit perturbation during inference without modifying the base model weights.
natural-language-processing transformers pytorch ai-safety statistical-detection gpt-2 pplm llm text-watermarking ai-content-detection
-
Updated
Feb 17, 2026 - Python