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, making them difficult to modify post-deployment without re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. This task is designed to facilitate rapid, data-efficient updates to KG embeddings without compromising the performance of other aspects. 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 hypernetwork to edit/add facts. Our comprehensive experimental results reveal that KGEditor excels in updating specific facts without impacting the overall performance, even when faced with limited training resources. Code and datasets are 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显著的实证成功。然而，基于语言模型的知识图谱嵌入通常作为静态工件部署，导致其在部署后难以在不重新训练的情况下进行修改。为解决这一问题，本文提出了一项新任务：编辑基于语言模型的知识图谱嵌入。该任务旨在实现对知识图谱嵌入的快速、数据高效更新，同时不损害其他方面的性能。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，结果表明先前模型在处理这一具有挑战性的新任务时能力有限。我们进一步提出一个简单但强大的基线方法 KGEditor，它利用超网络的额外参数层来编辑/添加事实。综合实验结果表明，即使面临有限的训练资源，KGEditor 在更新特定事实时仍能保持整体性能不受影响。代码和数据集可在 https://github.com/zjunlp/PromptKG/tree/main/deltaKG 获取。