How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances

Abstract

Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment.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 1 . LLMs align with ever-changing world knowledge Implicit ( §2.1) Knowledge Editing Meta-learning Editable Training (Sinitsin et al., 2020), RECKONING (Chen et al., 2023c)