Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained language models to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a general framework to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs) from various perspectives, which involves leveraging the reasoning, explanation, and summarization capabilities of LLMs to expand entity descriptions, understand relations, and extract structures, respectively. We conducted extensive evaluation of the effectiveness and improvement of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.
KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation
Research Institute of Cyberspace Security, Harbin Institute of Technology（哈尔滨工业大学网络空间安全研究院）；School of Computer Science and Technology, Harbin Institute of Technology at Weihai（哈尔滨工业大学（威海）计算机科学与技术学院）；Shandong Key Laboratory of Industrial Network Security（山东省工业网络安全重点实验室）；Department of Mathematics, Hong Kong Baptist University（香港浸会大学数学系）
Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；South-Central University for Nationalities（中南民族大学）
