AI 中文总结
该研究针对扩散语言模型解码时存在不必要去噪步骤的问题，提出生存引导式长度预测器，可将推理速度最高提升7倍且保持任务准确率，同时发现模型性能对所选预测长度敏感。
AI 中文摘要
扩散语言模型（DLM）通过迭代去噪掩码序列生成文本，但标准解码要么固定序列长度，要么依赖临时停止规则，常导致不必要的去噪步骤。我们将长度选择重新表述为序列结束标记上的离散时间生存问题，并提出一种即插即用、无需训练的长度预测器，可添加到任何现有DLM中。在推理和代码生成基准测试中，生存引导式长度解码将推理速度提升了最高7倍，同时保持了任务准确率。我们进一步发现，即使在同一数据集内，预测长度也差异很大，这使得模型性能对所选长度敏感。
英文摘要
Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7 times while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.
CommentsEMNLP 2026 (Main Conference)
