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.

翻译：大语言模型（LLMs）在事实性问答中展现了卓越能力，但有时仍会给出错误回答。为解决该问题，知识编辑技术作为修正LLMs中事实信息的有效手段应运而生。然而，典型的知识编辑工作流程难以确定最优编辑层集，并且依赖缺乏充分指导的汇总指标。这种可解释性不足阻碍了对最优编辑策略的有效比较与识别。本文提出KEditVis——一种新型可视分析系统，旨在通过交互式可视化帮助用户深入理解知识编辑过程、提升编辑效果，并为知识编辑算法的未来发展挖掘宝贵洞见。借助KEditVis，用户可选择合适层作为编辑目标，探索无效编辑的根本原因，并执行更具针对性与有效性的编辑。通过使用场景分析、专家访谈及用户研究等评估，我们验证了该系统的有效性与可用性。