研究人员引入了新的策略内蒸馏（OPD）方法，这是一种利用更强教师模型的反馈来训练学生 AI 模型的技术。两篇论文提出将监督集中在生成响应的特定、可“教会”的部分，而不是整个序列。这种方法被称为可教性感知 OPD（TA-OPD）和轨迹特定释放规则，旨在通过识别教师反馈最具有区分性和对学生最有用的地方来提高学习效率和性能。 AI
影响 这些方法可以通过将计算资源集中在信息量最大的反馈信号上，从而实现更高效的 AI 模型训练。
排序理由 该集群包含两篇详细介绍 AI 模型训练新研究方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.26844v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens.…
On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We revisit this principle and ask: which token-…
arXiv:2605.13643v2 Announce Type: replace Abstract: On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is available, supervising the full sequence of respo…