A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmentation Generation

ACL ARR 2025 February Submission183 Authors

Abstract: The integration of Knowledge Graphs (KGs) into the Retrieval Augmentation Generation (RAG) framework has attracted significant interest, with early studies showing promise in mitigating hallucinations and improving model accuracy. However, a systematic understanding and comparative analysis of the rapidly emerging KG-RAG methods are still lacking. This paper seeks to lay the foundation for systematically answering the question of when and how to use KG-RAG by analyzing their performance in various application scenarios associated with different technical configurations. After outlining the mind map using KG-RAG framework and summarizing its popular pipeline, we conduct a pilot empirical study of KG-RAG works to reimplement and evaluate 6 KG-RAG methods across 7 datasets in diverse scenarios, analyzing the impact of 9 KG-RAG configurations in combination with 17 LLMs. Our results underscore the critical role of appropriate application conditions and optimal configurations of KG-RAG components. The data and methods used, along with our reimplementation, are publicly available on https://anonymous.4open.science/r/Understanding-KG-RAG-EB54.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: Retrieval Augmentation Generation, Knowledge Graph, Large Language Model

Contribution Types: Reproduction study

Languages Studied: English, Chinese

Submission Number: 183