CLFeb 18, 2025

Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion

arXiv:2502.12598v114 citationsh-index: 24Proceedings of the First Workshop on Large Language Model Memorization (L2M2)
Originality Synthesis-oriented
AI Analysis

It addresses the need for LLMs to integrate diverse knowledge types for researchers and practitioners, but is incremental as a survey rather than a novel method.

This survey tackles the problem of adapting large language models (LLMs) to new knowledge by reviewing state-of-the-art methods for knowledge expansion, including techniques like continual learning and retrieval-based adaptation, to enhance their effectiveness in real-world applications.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes