AI RESEARCH
Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
arXiv CS.AI
•
ArXi:2603.22248v1 Announce Type: cross Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel generation of multiple tokens. However, this flexibility In this work, we develop the first theoretical analysis framework for confidence-based decoding in DLMs.