Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
This work addresses the problem of inconsistent evaluation standards for knowledge editing pitfalls in LLMs, which is incremental as it synthesizes existing findings into a comprehensive study.
The survey investigates the side effects of knowledge editing in large language models, such as knowledge distortion and general ability deterioration, by conducting experiments with consistent metrics and benchmarks to provide a unified perspective on these challenges.
Knowledge editing is a rising technique for efficiently updating factual knowledge in large language models (LLMs) with minimal alteration of parameters. However, recent studies have identified side effects, such as knowledge distortion and the deterioration of general abilities, that have emerged after editing. Despite these findings, evaluating the pitfalls of knowledge editing often relies on inconsistent metrics and benchmarks, lacking a uniform standard. In response, this survey presents a comprehensive study of these side effects, providing a unified perspective on the challenges of knowledge editing in LLMs by conducting experiments with consistent metrics and benchmarks. Additionally, we review related works and outline potential research directions to address these limitations. Our survey highlights the limitations of current knowledge editing methods, emphasizing the need for a deeper understanding of the inner knowledge structures of LLMs and improved knowledge editing methods. To foster future research, we have released the complementary materials publicly in https://github.com/MiuLab/EditLLM-Survey.