Knowledge Boundary of Large Language Models: A Survey

2024-12-17

arXiv.org

AI Summary

Large language models (LLMs) possess vast knowledge but suffer from ill-defined knowledge boundaries and hallucination-prone knowledge retrieval. Existing work lacks a formal, systematic characterization of these boundaries. This paper introduces the first formal definition of LLM knowledge boundaries and proposes the first taxonomy of LLM knowledge—categorizing knowledge into factual, procedural, context-dependent, and time-sensitive types. We further develop an integrated “motivation–identification–mitigation” analytical framework. Leveraging knowledge taxonomy modeling, systematic literature review, and cross-methodological synthesis, we identify six open challenges. Our work unifies fragmented research paradigms and establishes a theoretical foundation and practical guidance for designing knowledge-aware LLMs.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

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.

Problem

• Define knowledge boundary of LLMs
• Identify limitations in LLM knowledge utilization
• Propose mitigation strategies for knowledge boundary challenges

Innovation

• Define LLM knowledge boundary comprehensively
• Categorize knowledge into four distinct types
• Review motivation, identification, and mitigation strategies