Papers
arxiv:2508.08344

What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge

Published on Aug 11
Authors:
,
,
,
,
,
,
,

Abstract

A new method and evaluation protocol for assessing KG-RAG methods under knowledge incompleteness reveal limitations in reasoning and generalization.

AI-generated summary

Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include questions that can be directly answered using existing triples in KG, making it unclear whether models perform reasoning or simply retrieve answers directly. Moreover, inconsistent evaluation metrics and lenient answer matching criteria further obscure meaningful comparisons. In this work, we introduce a general method for constructing benchmarks, together with an evaluation protocol, to systematically assess KG-RAG methods under knowledge incompleteness. Our empirical results show that current KG-RAG methods have limited reasoning ability under missing knowledge, often rely on internal memorization, and exhibit varying degrees of generalization depending on their design.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.08344 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.08344 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.08344 in a Space README.md to link it from this page.

Collections including this paper 1