让离散扩散语言模型并行生成更准，不改模型也能用。
Mean-Field Parallel Decoding for Discrete Diffusion Language Models
- 用双向交互修正并行生成的冲突，提升一致性。
- 在推理时无需重训练，即可提高并行度和生成质量。
- 适合追求低延迟且不想改模型的开发者使用。
离散扩散语言模型支持并行生成，有望实现低延迟解码。然而，仅根据边际置信度独立选择词元会破坏并行性：单个位置看似可靠的词元，在多个位置同时更新时可能形成不兼容组合。本文提出一种无需训练的解码框架，协调这些并行更新。每次前向传播中，方法为每个掩码位置分配一个提交得分，并利用模型预测分布中的成对交互进行迭代优化。通过变分松弛，得到一个简单的固定点更新机制，能在一次前向传播中抑制冲突的并发提交。该机制使解码器在保持生成质量的前提下，可并行提交更多词元。方法轻量，无需辅助模型或重新训练，可无缝集成到现有扩散解码流程中。在推理与代码生成基准上的实验表明，该方法在质量-延迟权衡上实现了持续改进。
原文摘要 · Abstract (English)
Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding. However, selecting tokens independently by marginal confidence limits effective parallelism: tokens that appear reliable in isolation can form incompatible configurations when several positions are updated at once. We introduce a training-free decoding framework that coordinates these parallel updates. At each forward pass, the method assigns a commit score to each masked position and refines these scores using pairwise interactions derived from the model's predictive distributions. A variational relaxation yields a simple fixed-point update that suppresses conflicting simultaneous commitments within a single forward pass. This mechanism allows the decoder to commit more tokens in parallel while maintaining competitive generation quality. The method is lightweight, requires no auxiliary model or retraining, and drops into existing diffusion decoding pipelines without modification. Experiments on reasoning and code-generation benchmarks show consistent improvements in the quality-latency trade-off.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。