Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models
This work addresses the limitation of description-based knowledge graph completion for researchers and practitioners by providing a method to compensate for poor text quality and incomplete structures, though it is incremental as it builds on existing models.
The authors tackled the problem of incomplete knowledge graphs by proposing MPIKGC, a framework that uses large language models to enhance entity descriptions and relation understanding, achieving improved performance on link prediction and triplet classification tasks across four models and datasets.
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.