AI RESEARCH

BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models

arXiv CS.LG

ArXi:2601.06428v3 Announce Type: replace Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone self-correction framework that trains only a lightweight correction head on a finetuned DLM without updating any backbone or adapter parameters. Because the head is trained on errors produced by the same frozen generator used at inference time, its.