Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Dongzhuoran, Zhu, Yuqicheng, Wang, Xiaxia, He, Yuan, Chen, Jiaoyan, Staab, Steffen, Kharlamov, Evgeny
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916924318810112
author Zhou, Dongzhuoran
Zhu, Yuqicheng
Wang, Xiaxia
He, Yuan
Chen, Jiaoyan
Staab, Steffen
Kharlamov, Evgeny
author_facet Zhou, Dongzhuoran
Zhu, Yuqicheng
Wang, Xiaxia
He, Yuan
Chen, Jiaoyan
Staab, Steffen
Kharlamov, Evgeny
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05163
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness
Zhou, Dongzhuoran
Zhu, Yuqicheng
Wang, Xiaxia
He, Yuan
Chen, Jiaoyan
Staab, Steffen
Kharlamov, Evgeny
Artificial Intelligence
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.
title Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness
topic Artificial Intelligence
url https://arxiv.org/abs/2504.05163