大型语言模型的持续学习：一项全面综述
Continual Learning of Large Language Models: A Comprehensive Survey
AI总结：
该综述系统梳理了大型语言模型持续学习的研究进展，提出垂直与水平连续性框架，总结持续预训练、领域自适应预训练和持续微调三个阶段，并概述评估协议与数据源。
摘要：
近期，在静态、预先收集的通用数据集上训练的大型语言模型（LLMs）取得了显著成功，引发了众多研究方向和应用。其中一个方向致力于解决将预训练LLMs整合到动态数据分布、任务结构和用户偏好中的非平凡挑战。针对特定需求进行定制时，预训练LLMs往往会在先前知识领域出现显著的性能退化，这一现象被称为“灾难性遗忘”。尽管持续学习（CL）领域已对该问题进行了广泛研究，但它在LLMs领域呈现出新的表现形式。在本综述中，我们全面概述了LLMs在持续学习背景下的当前研究进展。本综述分为四个主要部分：首先描述持续学习LLMs的总体概览，包括两个连续性方向：垂直连续性（或垂直持续学习），即从通用能力到特定能力的持续适应；以及水平连续性（或水平持续学习），即跨时间和跨领域的持续适应（第3节）。然后，我们总结了现代持续学习背景下LLMs学习的三个阶段：持续预训练（CPT）、领域自适应预训练（DAP）和持续微调（CFT）（第4节）。接着，我们概述了LLMs持续学习的评估协议以及当前可用的数据源（第5节）。最后，我们讨论了与LLMs持续学习相关的引人关注的问题（第6节）。本综述所考察论文的完整列表可在 https://github.com/Wang-ML-Lab/llm-continual-learning-survey 获取。
英文摘要：
The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction addresses the non-trivial challenge of integrating pre-trained LLMs into dynamic data distributions, task structures, and user preferences. Pre-trained LLMs, when tailored for specific needs, often experience significant performance degradation in previous knowledge domains -- a phenomenon known as "catastrophic forgetting". While extensively studied in the continual learning (CL) community, it presents new manifestations in the realm of LLMs. In this survey, we provide a comprehensive overview of the current research progress on LLMs within the context of CL. This survey is structured into four main sections: we first describe an overview of continually learning LLMs, consisting of two directions of continuity: vertical continuity (or vertical continual learning), i.e., continual adaptation from general to specific capabilities, and horizontal continuity (or horizontal continual learning), i.e., continual adaptation across time and domains (Section 3). We then summarize three stages of learning LLMs in the context of modern CL: Continual Pre-Training (CPT), Domain-Adaptive Pre-training (DAP), and Continual Fine-Tuning (CFT) (Section 4). Then we provide an overview of evaluation protocols for continual learning with LLMs, along with the current available data sources (Section 5). Finally, we discuss intriguing questions pertaining to continual learning for LLMs (Section 6). The full list of papers examined in this survey is available at https://github.com/Wang-ML-Lab/llm-continual-learning-survey.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
