Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deployed as static artifacts, which are challenging to modify without re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. The proposed task aims to enable data-efficient and fast updates to KG embeddings without damaging the performance of the rest. We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hyper network to edit/add facts. Comprehensive experimental results demonstrate that KGEditor can perform better when updating specific facts while not affecting the rest with low training resources. Code and datasets will be available in https://github.com/zjunlp/PromptKG/tree/main/deltaKG.

翻译：近年来，基于语言模型构建知识图谱嵌入取得了实证成功。然而，这类嵌入通常以静态形式部署，在部署后若需修改则面临重新训练的挑战。为解决该问题，本文提出一项新任务——编辑基于语言模型的知识图谱嵌入。该任务旨在实现低数据依赖且快速的知识图谱嵌入更新，同时不损害其他部分的性能。我们构建了四个新数据集：E-FB15k237、A-FB15k237、E-WN18RR 和 A-WN18RR，并评估了多种知识编辑基线方法，结果表明现有模型在处理这一挑战性任务时能力有限。我们进一步提出一个简单而强大的基线模型 KGEditor，该模型利用超网络的附加参数层来编辑/添加事实。全面的实验结果表明，KGEditor 在更新特定事实时性能更优，且能以较低训练资源保持其余部分不受影响。代码与数据集将发布于 https://github.com/zjunlp/PromptKG/tree/main/deltaKG。