Research Trends for the Interplay between Large Language Models and Knowledge Graphs

TL;DR

This survey addresses the problem of integrating Large Language Models (LLMs) with Knowledge Graphs (KGs) to enhance understanding, reasoning, and language processing. It categorizes interactions into three modalities—LLMs for KG construction, KG-enhanced LLMs, and direct LLM-KG cooperation—and analyzes methods across KG construction, validation, reasoning, embedding, and QA. Key contributions include a comprehensive taxonomy of LLM-KG interactions, a synthesis of methodologies (e.g., KG-to-text, retrieval-augmented generation, neurosymbolic alignment), and open challenges such as reliable knowledge incorporation, bias mitigation, and scalability. The findings inform literature and practice, offering directions for future research and practical deployment of LLM-KG systems in AI applications.

Abstract

This survey investigates the synergistic relationship between Large Language Models (LLMs) and Knowledge Graphs (KGs), which is crucial for advancing AI's capabilities in understanding, reasoning, and language processing. It aims to address gaps in current research by exploring areas such as KG Question Answering, ontology generation, KG validation, and the enhancement of KG accuracy and consistency through LLMs. The paper further examines the roles of LLMs in generating descriptive texts and natural language queries for KGs. Through a structured analysis that includes categorizing LLM-KG interactions, examining methodologies, and investigating collaborative uses and potential biases, this study seeks to provide new insights into the combined potential of LLMs and KGs. It highlights the importance of their interaction for improving AI applications and outlines future research directions.

Figures (2)

• Figure 1: Categorization of the interplay between LLMs and KGs
• Figure 2: Statistics of the usage of LLMs and KGs in cited papers per category