面向掩码扩散机器翻译的长度自适应解码

摘要

机器翻译测试了掩码扩散语言模型（dLLMs），因为每个源语token都必须被忠实呈现，而固定画布解码必须在去噪之前确定目标长度。现有的掩码扩散解码工作主要研究token去掩码顺序，尽管长度决策对覆盖率和冗余度有直接影响，但该决策仍未得到充分探索。我们提出熵谷（Entropy-Valley，EV），一种免训练的长度选择器，通过对全掩码前向传播的平均预测熵对候选目标画布进行评分，并选择骨干模型最有准备填充的画布。相较于使用训练语料长度统计作为基线的方案，EV在EntoZh、ZhtoEn和EntoDe上分别恢复了参考目标长度下COMET-22增益的64.9%、65.3%和33.0%。我们的诊断表明，有利于去噪的长度无需与参考长度一致。三位翻译专家的评估支持英汉双向的充分性提升，其中ZhtoEn方向的证据更为充分。与使用相同微调数据训练的LLaMA-3-8B自回归（AR）模型相比，EV系统在EntoZh上持平，在ZhtoEn上领先；进一步的神谕长度诊断表明，在这种掩码扩散MT设置中，决定先揭示哪些token不如目标长度的提供方式重要。

English

Machine translation tests masked diffusion language models (dLLMs) because every source token must be rendered faithfully, while fixed canvas decoding must choose target length before denoising. Existing masked diffusion decoding work mainly studies token unmasking order, leaving this length decision under-explored despite its direct effect on coverage and redundancy. We introduce Entropy-Valley (EV), a training-free length selector that scores candidate target canvases by mean predictive entropy from all-mask forward passes and selects the canvas the backbone is most prepared to fill. Relative to a baseline using training corpus length statistics, EV recovers 64.9%, 65.3%, and 33.0% of the COMET-22 gain from reference target lengths on EntoZh, ZhtoEn, and EntoDe. Our diagnostics show that denoising-friendly lengths need not match reference lengths. Evaluation by three translation experts supports the EnleftrightarrowZh adequacy gains, with stronger evidence on ZhtoEn. Compared with a LLaMA-3-8B autoregressive (AR) model trained on the same fine-tuning data, the EV system ties on EntoZh and leads on ZhtoEn; an oracle-length diagnostic further shows that, in this masked diffusion MT setting, deciding which tokens to reveal first matters less than how the target length is supplied.