Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models

Excerpt

arXiv:2609.25927v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have emerged as an efficient alternative to autoregressive models, yet aligning them via Reinforcement Learning (RL) requires likelihood surrogates estimated from masked reconstruction subproblems under a small Monte Carlo budget per rollout. Existing methods construct these subproblems by uniform random masking, leaving open the question of which subproblems to prioritize. We identify a systematic upstream/d