Google Research 提出睡眠框架：让 LLM 在持续学习中保留知识
原标题：The sleep framework: A new way for LLMs to retain knowledge in continual learning
AI 摘要
Google Research 提出一种面向大语言模型持续学习的“睡眠框架”，通过模拟人类睡眠的记忆巩固与梦境阶段，让模型在部署后周期性进行离线自我更新。该方法利用预分配的 MoE 记忆块和自生成练习样本更新权重，旨在缓解灾难性遗忘和静态知识截止问题。实验显示，该方法在长上下文理解上可扩展至 1000 万 token，并在多语言持续翻译中保持接近零的性能下降。
正文节选
October 27, 2026 Ali Behrouz and Vahab Mirrokni, Google Research We introduce a sleep phase in continual learning, enabling large language models to continuously integrate new facts and enhance reasoning while mitigating catastrophic forgetting or static knowledge cutoffs. Modern LLMs achieve impressive performance via pre-training and in-context learning (ICL). However, once deployed, they remain largely static, operating with a fixed knowledge cutoff date that leaves them unable to acquire lon