PulseAugur
中
实时 20:39:32
English(EN) RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

RISE 方法通过自外推增强语言模型训练

研究人员推出了一种新颖的、通过自外推策略蒸馏来改进语言模型训练后性能的方法——RISE。该技术利用模型自身的强化学习轨迹构建一个合成教师,将稀疏的结果诱导更新转化为密集的 token 级目标,无需外部模型。RISE 在人类反馈强化学习 (RLHF) 和 On-Policy Distillation (OPD) 之间形成一个循环,其中结果奖励指导外推,而外推的教师则优化 token 决策。实验表明,RISE 在数学推理、STEM 和代码生成等各种任务上的表现优于现有方法。 AI

影响 该方法通过改进自蒸馏技术,有望实现更高效、更有效的语言模型训练。

排序理由 该集群描述了一篇详细介绍一种新颖的语言模型训练方法的最新研究论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

RISE 方法通过自外推增强语言模型训练

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇详细介绍一种新颖的语言模型训练方法的最新研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
48 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yang Li, Semih Yavuz, Shafiq Joty ·

    RISE: 通过自外推策略蒸馏的递归改进

    arXiv:2609.05295v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillat…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    RISE: 通过自外推策略蒸馏实现递归改进

    RISE improves language model post-training by recursively generating dense token-level supervision from the model's own reinforcement learning trajectory via self-extrapolation, avoiding external teachers.