研究人员推出了一种新的框架DRIFT，旨在提高大型语言模型进行多轮交互训练的效率。DRIFT解决了昂贵的在线强化学习与效果较差的离线监督微调之间的权衡问题。通过将轨迹采样与优化解耦并使用重要性权重，DRIFT在保持监督微调的简洁性和效率的同时，实现了与强化学习相当的性能。 AI
影响 能够更有效地训练LLM用于交互式、多轮应用。
排序理由 该集群包含一篇详细介绍LLM优化新方法的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2605.31455v1 Announce Type: cross Abstract: Large language models are increasingly deployed in multi-turn interactive settings where users or environments can iteratively provide lightweight feedback. Unfortunately, optimizing such behavior presents a sharp dilemma in pract…
Large language models are increasingly deployed in multi-turn interactive settings where users or environments can iteratively provide lightweight feedback. Unfortunately, optimizing such behavior presents a sharp dilemma in practice: online reinforcement learning is able to effe…
DRIFT is a framework that combines offline trajectories with importance-weighted supervised fine-tuning to achieve multi-turn interactive learning efficiency and performance comparable to reinforcement learning.