|国家预印本平台
首页|Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation

Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation

Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation

来源:Arxiv_logoArxiv
英文摘要

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.

Nikita Mounier、Parsa Idehpour

计算技术、计算机技术

Nikita Mounier,Parsa Idehpour.Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation[EB/OL].(2025-07-07)[2025-08-02].https://arxiv.org/abs/2507.08018.点此复制

评论