SOURCE-LINKED INTELLIGENCE

DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, independently predicting multiple tokens at each step. This conditional independence discards inter-token dependencies and degrades coherence-an issue that parallels the multi-modality problem in Non-Autoregressive Translation (NAT). Drawing on the Directed Acyclic Transformer (DAT), which tackles this problem in NAT via a Directed Acyclic Graph (DAG), we propose DA-DLM, a model that adapts DAG-based dependency modeling to DLMs' iterative setting through a position-oriented DAG design. The position-orien

Read original source ↗ Open in workspace

recordType

paper

region

Global