AI RESEARCH
dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
arXiv CS.LG
•
ArXi:2601.22985v2 Announce Type: replace We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor would be invariant to this order, practical dLLMs exhibit strong sensitivity to the unmasking order, creating a new channel for watermarking.