The task of predicting multiple links within knowledge graphs (KGs) stands as a challenge in the field of knowledge graph analysis, a challenge increasingly resolvable due to advancements in natural language processing (NLP) and KG embedding techniques. This paper introduces a novel methodology, the Knowledge Graph Large Language Model Framework (KG-LLM), which leverages pivotal NLP paradigms, including chain-of-thought (CoT) prompting and in-context learning (ICL), to enhance multi-hop link prediction in KGs. By converting the KG to a CoT prompt, our framework is designed to discern and learn the latent representations of entities and their interrelations. To show the efficacy of the KG-LLM Framework, we fine-tune three leading Large Language Models (LLMs) within this framework, employing both non-ICL and ICL tasks for a comprehensive evaluation. Further, we explore the framework's potential to provide LLMs with zero-shot capabilities for handling previously unseen prompts. Our experimental findings discover that integrating ICL and CoT not only augments the performance of our approach but also significantly boosts the models' generalization capacity, thereby ensuring more precise predictions in unfamiliar scenarios.

翻译：在知识图谱中预测多重链接的任务是知识图谱分析领域的一项挑战，而随着自然语言处理（NLP）和知识图谱嵌入技术的进步，这一挑战正日益变得可解。本文提出了一种新颖方法论——知识图谱大语言模型框架（KG-LLM），该框架利用关键的NLP范式，包括思维链（CoT）提示和情境学习（ICL），以增强知识图谱中的多跳链接预测。通过将知识图谱转化为CoT提示，我们的框架旨在识别并学习实体及其相互关系的潜在表示。为展示KG-LLM框架的有效性，我们在该框架内对三种领先的大语言模型（LLM）进行了微调，并通过非ICL和ICL任务进行综合评估。此外，我们探索了该框架为LLM提供零样本能力的潜力，以处理之前未见过的提示。我们的实验发现，整合ICL和CoT不仅增强了我们方法的性能，还显著提升了模型的泛化能力，从而确保在陌生场景中实现更精确的预测。