梳理大模型知识边界，揭示其认知极限与改进方向
Knowledge Boundary of Large Language Models: A Survey
- 提出大模型知识边界的系统化定义与四类知识分类
- 归纳识别知识边界的方法与应对策略，涵盖动机、检测与优化
- 适合关注模型可靠性、知识管理与安全性的研究者参考
尽管大语言模型（LLMs）在其参数中存储了海量知识，但在特定知识的记忆与利用上仍存在局限，导致生成不实或错误内容。这凸显了理解大模型知识边界的重要性，而该概念在现有研究中尚未明确定义。本文提出一个全面的知识边界定义，并引入形式化的分类体系，将知识划分为四类。基于此，从三个关键视角系统回顾该领域：研究知识边界的动机、识别方法及应对挑战的策略。最后讨论未解难题与潜在研究方向。本综述旨在为社区提供全景式概览，促进关键问题的探索，推动大模型知识研究的发展。
原文摘要 · Abstract (English)
Although large language models (LLMs) store vast amount of knowledge in their parameters, they still have limitations in the memorization and utilization of certain knowledge, leading to undesired behaviors such as generating untruthful and inaccurate responses. This highlights the critical need to understand the knowledge boundary of LLMs, a concept that remains inadequately defined in existing research. In this survey, we propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. Using this foundation, we systematically review the field through three key lenses: the motivation for studying LLM knowledge boundaries, methods for identifying these boundaries, and strategies for mitigating the challenges they present. Finally, we discuss open challenges and potential research directions in this area. We aim for this survey to offer the community a comprehensive overview, facilitate access to key issues, and inspire further advancements in LLM knowledge research.
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。