@inproceedings{zhou-etal-2026-breaks,
    title = "What Breaks Knowledge Graph based {RAG}? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge",
    author = "Zhou, Dongzhuoran  and
      Zhu, Yuqicheng  and
      Wang, Xiaxia  and
      Zhou, Hongkuan  and
      He, Yuan  and
      Chen, Jiaoyan  and
      Staab, Steffen  and
      Kharlamov, Evgeny",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.114/",
    pages = "2522--2538",
    ISBN = "979-8-89176-380-7",
    abstract = "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 and present BRINK (Benchmark for Reasoning under Incomplete Knowledge) 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."
}