|国家预印本平台
首页|What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Dongzhuoran Zhou、Yuqicheng Zhu、Xiaxia Wang、Hongkuan Zhou、Yuan He、Jiaoyan Chen、Evgeny Kharlamov、Steffen Staab

计算技术、计算机技术

Dongzhuoran Zhou,Yuqicheng Zhu,Xiaxia Wang,Hongkuan Zhou,Yuan He,Jiaoyan Chen,Evgeny Kharlamov,Steffen Staab.What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge[EB/OL].(2025-08-11)[2025-08-24].https://arxiv.org/abs/2508.08344.点此复制

评论