Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yield greater efficiency. Yet, in practice, current open-source DLMs often underperform their AR counterparts in speed, limiting their real-world utility. This work presents a systematic study of DLM efficiency, identifying key issues in prior evaluation methods. Through empirical benchmarking and a theoretical analysis, we demonstrate that AR models generally achieve higher throughput, while DLMs consistently lag. We also investigate acceleration strategies, finding that techniques like dual cache and parallel decoding mainly offer gains at small batch sizes, with their benefits diminishing upon scaling. Our findings underscore the necessity of robust evaluation methods and improved acceleration strategies to advance research on DLMs.
@article{arxiv.2510.18480,
title = {How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices},
author = {Han Peng and Peiyu Liu and Zican Dong and Daixuan Cheng and Junyi Li and Yiru Tang and Shuo Wang and Wayne Xin Zhao},
journal= {arXiv preprint arXiv:2510.18480},
year = {2025}
}