A Dual-Axis Taxonomy of Knowledge Editing for LLMs: From Mechanisms to Functions
It addresses the need for efficient knowledge updates in LLMs without full retraining, offering a novel framework for researchers and practitioners, though it is incremental as it builds on existing surveys.
This survey tackles the problem of outdated or inaccurate knowledge in large language models by proposing a dual-axis taxonomy for knowledge editing, focusing on both mechanisms and functions to provide a holistic view of the field.
Large language models (LLMs) acquire vast knowledge from large text corpora, but this information can become outdated or inaccurate. Since retraining is computationally expensive, knowledge editing offers an efficient alternative -- modifying internal knowledge without full retraining. These methods aim to update facts precisely while preserving the model's overall capabilities. While existing surveys focus on the mechanism of editing (e.g., parameter changes vs. external memory), they often overlook the function of the knowledge being edited. This survey introduces a novel, complementary function-based taxonomy to provide a more holistic view. We examine how different mechanisms apply to various knowledge types -- factual, temporal, conceptual, commonsense, and social -- highlighting how editing effectiveness depends on the nature of the target knowledge. By organizing our review along these two axes, we map the current landscape, outline the strengths and limitations of existing methods, define the problem formally, survey evaluation tasks and datasets, and conclude with open challenges and future directions.