Skip to content
arXiv cs.CL · Papers

Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models

arXiv:2608.02625v1 Announce Type: new Abstract: Diffusion language models (DLMs) can revise tokens bidirectionally, but standard decoding procedures often adapt them to left-to-right generation by producing text block by block. We study a simple plug-and-play inference pattern: first generate a complete draft, then ref