提出一种扩散语言模型测试时自验证方法，提升生成质量与稳定性。
Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models
- 通过前缀条件重生成检测生成轨迹稳定性
- 在数学与常识推理任务上显著优于初始生成结果
- 适合追求高可靠性的生成系统部署者
扩散语言模型（DLMs）近年来在性能上已可媲美自回归模型，甚至在某些任务中表现更优。与自回归模型不同，DLMs 通过迭代去噪生成输出，不依赖从左到右的顺序。为进一步提升 DLM 性能，本文提出 PDC（Prefix-Denoising Consistency），一种针对 DLMs 的测试时自验证方法。PDC 利用前缀条件再生过程中的独特测试时信号：正确轨迹比错误轨迹更稳定、可重复。具体而言，给定一个初始生成样本，PDC 在中间位置分割句子，并以固定前缀重新生成剩余标记。在数学推理和常识推理基准上，PDC 均持续改进初始样本，在计算资源受限条件下优于独立生成，且对不同去掩码策略和参数设置具有鲁棒性。这些结果表明，前缀条件再生是 DLM 特有的有效测试时验证原语。
原文摘要 · Abstract (English)
Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain tasks. Unlike AR models, DLMs produce output through iterative denoising without a left-to-right order. To further improve the performance of DLMs, we introduce PDC (\emph{Prefix-Denoising Consistency}), a test-time self-verification method for DLMs. PDC exploits a distinctive test-time signal in DLMs under prefix conditioned regeneration, correct trajectories are more stable and reproducible than incorrect ones. Concretely, given an initially generated sample, PDC splits the sentence at an intermediate position and regenerates the remaining tokens conditioned on the fixed prefix. Across mathematical reasoning and commonsense reasoning benchmarks, PDC consistently improves upon the initial sample, outperforms independent generations under a computational constrained comparison, and is robust to different unmasking strategies and parameter settings. These results highlight prefix-conditioned regeneration as an effective DLM-specific primitive for test-time verification.
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。