梳理大模型知识扩展方法，助其持续学习新知识。
Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion
- 整合事实、领域专长等多类知识，提升模型适应性
- 涵盖持续学习、模型编辑等主流知识扩展技术
- 适合想让大模型长期保持知识更新的研究者
将大语言模型（LLMs）适配到新且多样的知识是其实现长期有效性的关键。本文综述了当前最先进的大模型知识扩展方法，重点聚焦于整合各类知识，包括事实信息、领域专长、语言能力及用户偏好。我们探讨了持续学习、模型编辑和基于检索的显式适配等技术，并讨论了知识一致性与可扩展性等挑战。本综述旨在为研究人员和实践者提供指导，揭示推动大模型成为可适应、强健的知识系统的发展机遇。
原文摘要 · Abstract (English)
Adapting large language models (LLMs) to new and diverse knowledge is essential for their lasting effectiveness in real-world applications. This survey provides an overview of state-of-the-art methods for expanding the knowledge of LLMs, focusing on integrating various knowledge types, including factual information, domain expertise, language proficiency, and user preferences. We explore techniques, such as continual learning, model editing, and retrieval-based explicit adaptation, while discussing challenges like knowledge consistency and scalability. Designed as a guide for researchers and practitioners, this survey sheds light on opportunities for advancing LLMs as adaptable and robust knowledge systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。