KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models
This addresses the lack of transparency in knowledge editing workflows for LLM developers and researchers, though it is incremental as it builds on existing editing techniques.
The paper tackles the problem of correcting factual errors in Large Language Models (LLMs) by introducing KEditVis, a visual analytics system that helps users select optimal layers for editing and understand ineffective edits, validated through user studies.
Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for correcting factual information in LLMs. However, typical knowledge editing workflows struggle with identifying the optimal set of model layers for editing and rely on summary indicators that provide insufficient guidance. This lack of transparency hinders effective comparison and identification of optimal editing strategies. In this paper, we present KEditVis, a novel visual analytics system designed to assist users in gaining a deeper understanding of knowledge editing through interactive visualizations, improving editing outcomes, and discovering valuable insights for the future development of knowledge editing algorithms. With KEditVis, users can select appropriate layers as the editing target, explore the reasons behind ineffective edits, and perform more targeted and effective edits. Our evaluation, including usage scenarios, expert interviews, and a user study, validates the effectiveness and usability of the system.