Relations Prediction for Knowledge Graph Completion using Large Language Models

TL;DR

This paper leverages large language models fine-tuned on node names to predict relations in knowledge graphs, enabling effective inductive reasoning and achieving new benchmark scores.

Contribution

It introduces a novel approach using only node names for relation prediction, enhancing inductive capabilities in knowledge graph completion.

Findings

Achieved new state-of-the-art scores on a standard benchmark.

Demonstrated effective inductive relation prediction using only node names.

Showed that large language models can be fine-tuned for knowledge graph tasks.

Abstract

Knowledge Graphs have been widely used to represent facts in a structured format. Due to their large scale applications, knowledge graphs suffer from being incomplete. The relation prediction task obtains knowledge graph completion by assigning one or more possible relations to each pair of nodes. In this work, we make use of the knowledge graph node names to fine-tune a large language model for the relation prediction task. By utilizing the node names only we enable our model to operate sufficiently in the inductive settings. Our experiments show that we accomplish new scores on a widely used knowledge graph benchmark.