Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position

Zhixin Xie; Xurui Song; Jun Luo

AAAI 2026technical0 citations

Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position

Abstract

Diffusion Large Language Models (dLLMs) have recently emerged as a competitive non-autoregressive paradigm due to their unique training and inference approach. However, there is currently a lack of safety study on this novel architecture. In this paper, we present the first analysis of dLLMs

BibTeX

@inproceedings{aaai2026_wheretostartalig,
  title = {Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position},
  author = {Zhixin Xie and Xurui Song and Jun Luo},
  booktitle = {AAAI 2026},
  year = {2026}
}