Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness
This addresses the problem of unreliable KG-RAG performance in realistic settings with incomplete knowledge graphs for researchers and practitioners in question answering systems.
The paper systematically evaluates Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) methods under incomplete knowledge graphs by removing triples and analyzing performance effects, demonstrating that these methods are sensitive to KG incompleteness.
Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) is a technique that enhances Large Language Model (LLM) inference in tasks like Question Answering (QA) by retrieving relevant information from knowledge graphs (KGs). However, real-world KGs are often incomplete, meaning that essential information for answering questions may be missing. Existing benchmarks do not adequately capture the impact of KG incompleteness on KG-RAG performance. In this paper, we systematically evaluate KG-RAG methods under incomplete KGs by removing triples using different methods and analyzing the resulting effects. We demonstrate that KG-RAG methods are sensitive to KG incompleteness, highlighting the need for more robust approaches in realistic settings.