Knowledge graphs play a vital role in numerous artificial intelligence tasks, yet they frequently face the issue of incompleteness. In this study, we explore utilizing Large Language Models (LLM) for knowledge graph completion. We consider triples in knowledge graphs as text sequences and introduce an innovative framework called Knowledge Graph LLM (KG-LLM) to model these triples. Our technique employs entity and relation descriptions of a triple as prompts and utilizes the response for predictions. Experiments on various benchmark knowledge graphs demonstrate that our method attains state-of-the-art performance in tasks such as triple classification and relation prediction. We also find that fine-tuning relatively smaller models (e.g., LLaMA-7B, ChatGLM-6B) outperforms recent ChatGPT and GPT-4.

翻译：知识图谱在众多人工智能任务中发挥着至关重要的作用，然而它们常常面临不完整性问题。在本研究中，我们探索利用大型语言模型（LLM）进行知识图谱补全。我们将知识图谱中的三元组视为文本序列，并引入了一种名为知识图谱大型语言模型（KG-LLM）的创新框架来建模这些三元组。我们的技术将三元组的实体和关系描述作为提示，并利用响应进行预测。在多个基准知识图谱上的实验表明，我们的方法在三元组分类和关系预测等任务中达到了领先水平。我们还发现，微调相对较小的模型（如LLaMA-7B、ChatGLM-6B）优于最近的ChatGPT和GPT-4。