KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion

Yanbin Wei, Qiushi Huang, Yu Zhang, James Kwok

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: Information Retrieval and Text Mining

Keywords: Knowledge Graph Completion, Large Language Model

Abstract: Knowledge Graph Completion (KGC) is crucial for addressing knowledge graph incompleteness and supporting downstream applications. Many models have been proposed for KGC and they can be categorized into two main classes, including triple-based and test-based approaches. Triple-based methods struggle with long-tail entities due to limited structural information and imbalanced distributions of entities. Text-based methods alleviate this issue but require costly training for language models and specific finetuning for knowledge graphs, which limits their efficiency. To alleviate the limitations in the two approaches, in this paper, we propose KICGPT, a framework that integrates a large language model (LLM) and a triple-based KGC retriever, to alleviate the long-tail problem without incurring additional training overhead. In the proposed KICGPT model, we propose an in-context learning strategy called Knowledge Prompt, which encodes structural knowledge into demonstrations to guide LLM. Empirical results on benchmark datasets demonstrate the effectiveness of the proposed KICGPT model with lighter training overhead and no finetuning.

Submission Number: 405