研究人员推出了一种用于大型语言模型自蒸馏的新方法——轨迹增强策略优化（TAPO）。与最小化KL散度的传统方法不同，TAPO通过保留错误推理直至失败点，然后纳入自然语言诊断和纠正的推理来构建显式的训练轨迹。该方法旨在提供更精细的错误纠正，并在AIME 2024、AIME 2025和HMMT 2025的实验中显示出比GRPO持续的改进。 AI
影响 该方法通过提供有针对性的错误纠正，可能导致更有效和高效的LLM训练。
排序理由 该集群包含一篇详细介绍LLM自蒸馏新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distributio…
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generate…