通过三步流程提升文本生成质量，无需训练即可优化模型输出。
Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation
- 用评分模型评估生成片段，识别潜在错误。
- 低分片段更多词被遮蔽，引导重点重生成。
- 适配任意预训练掩码扩散模型，可直接部署。
迭代式文本生成面临的核心挑战是如何让模型高效识别并修正自身错误。我们提出无需额外训练的R3框架（Review, Remask, Refine），适用于任意预训练掩码文本扩散模型（如LLaDA或BD3-LM）。R3利用过程奖励模型（PRM）对中间生成块进行评审；根据PRM得分制定重遮蔽策略：得分越低，表明可能出错，该块中被遮蔽的词比例越高；最后强制模型对这些区域进行精细化重生成，集中改进历史生成中的次优部分，从而提升最终输出质量。
原文摘要 · Abstract (English)
A key challenge for iterative text generation is enabling models to efficiently identify and correct their own errors. We propose Review, Remask, Refine (R3), a relatively simple yet elegant framework that requires no additional model training and can be applied to any pre-trained masked text diffusion model (e.g., LLaDA or BD3-LM). In R3, a Process Reward Model (PRM) is utilized for the Review of intermediate generated blocks. The framework then translates these PRM scores into a Remask strategy: the lower a block's PRM score, indicating potential mistakes, the greater the proportion of tokens within that block are remasked. Finally, the model is compelled to Refine these targeted segments, focusing its efforts more intensively on specific sub-optimal parts of past generations, leading to improved final output.
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。