Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing concern in the current era. This paper provides a comprehensive review of recent advances in aligning LLMs with the ever-changing world knowledge without re-training from scratch. We categorize research works systemically and provide in-depth comparisons and discussion. We also discuss existing challenges and highlight future directions to facilitate research in this field. We release the paper list at https://github.com/hyintell/awesome-refreshing-llms

翻译：尽管大型语言模型（LLMs）在解决各类任务中表现出色，但它们在部署后可能迅速过时。如何保持其知识更新是当前时代的一个紧迫问题。本文系统梳理了无需从头重新训练即可使LLMs与持续变化的世界知识保持对齐的最新进展。我们对相关研究工作进行了系统性分类，并提供了深入的比较与讨论。此外，本文还探讨了现有挑战，并指出了未来研究方向，以推动该领域的发展。相关论文列表发布在 https://github.com/hyintell/awesome-refreshing-llms