arXiv：cs.AI· Jiahao Kuang, Yangfan Gao, Tao Gui, Yuanbin Wu, Qi Zhang, Xuanjing Huang, Tao Ji·· 22 小时前
RePara：强化 Diffusion LLM 并行生成能力
A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs
AI 导读
针对扩散大语言模型并行生成的固定配额评测显示，四款代表性模型在数学与代码任务上严重退化，每步 16 tokens 时所有得分低于 15%。为此提出的 RePara 通过组相对策略优化强化短连续 token 块，并降低 rollout 与 log-probability 重算成本。
正文
Abstract:Parallel generation is widely regarded as an inherent advantage of diffusion large language models. Yet our fixed-quota evaluation of four representative models reveals severe degradation across mathematics and code, with all scores below 15% at 16 tokens per step. Token-level probes identify local predictive potential near the observed prefix, especially in mathematical text. We propose RePara, which reinforces short consecutive token blocks through group-relative policy optimization and reduces rollout and log-probability recomputation costs. On LLaDA and SDAR, \ours improves GSM8K and MATH-500 accuracy over JustGRPO under reduced denoising budgets, with a 1.96x training-step speedup in our LLaDA/MATH setup.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18200 [cs.LG] |
| (or arXiv:2610.18200v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18200 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiahao Kuang [view email]
[v1]
Tue, 13 Oct 2026 11:37:04 UTC (424 KB)
来源：arXiv：cs.AI · arxiv.org