KEditVis帮助用户可视化定位LLM知识编辑的最佳层，提升纠错效果。
KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models
- 通过交互式可视化分析，定位最优编辑层
- 可探究无效编辑原因，指导精准修正
- 适合模型优化与知识编辑研究者使用
大型语言模型（LLMs）在事实问答中表现优异，但常给出错误答案。知识编辑技术被提出以修正模型中的事实性错误，但传统工作流难以确定最佳编辑层，且依赖的总结指标缺乏指导性，透明度不足，阻碍了有效比较和策略选择。本文提出KEditVis，一个新型可视化分析系统，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，并发现未来算法发展的关键洞察。用户可通过该系统选择合适的编辑层，探索无效编辑的原因，实现更精准、高效的编辑操作。通过使用场景分析、专家访谈和用户研究评估，验证了系统的有效性与可用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。