$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing

ArXi:2605.25893v1 Announce Type: new Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring for D-LLMs remains largely unexplored. Unlike AR-LLMs, D-LLMs generate text through a multi-step denoising process, exposing intermediate hidden representations that may contain safety-relevant information unavailable in standard single-step monitoring setups.