AI 中文总结
研究块扩散语言模型的采样，基于其更适合从左到右解码的特点，提出并行自回归解码方法PARD，该方法无需训练，能保留结构并允许并行令牌承诺，实验证明其在生成质量和速度上优于现有方法。
AI 中文摘要
扩散语言模型支持灵活的任意顺序生成，但现有采样方法大多针对早期掩码扩散模型（MDMs）设计。本文研究了近期块扩散语言模型（BDLMs）的采样。通过实证和分析表明，这些模型比MDMs更符合从左到右解码。基于此，提出了并行自回归解码（PARD），一种简单的无需训练的采样方法，在保留从左到右解掩码结构的同时允许并行令牌承诺。大量实验表明，PARD在生成质量上始终优于现有并行采样器，且在速度上比纯自回归解码有大幅提升，质量差距小。
英文摘要
Diffusion language models enable flexible arbitrary-order generation, but existing sampling methods are mostly designed for early masked diffusion models (MDMs). In this work, we study sampling for recent block diffusion language models (BDLMs). We show empirically and analytically that these models are naturally more aligned with left-to-right decoding than MDMs. Based on this observation, we propose Parallel Autoregressive Decoding (PARD), a simple training-free sampling method that preserves left-to-right unmasking structure while allowing parallel token commitment. Extensive experiments show that PARD consistently outperforms existing parallel samplers in generation quality, while achieving substantial speedups over pure AR decoding with only a small quality gap.
Comments20 pages, 15 figures, 6 tables
