What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge
什么破坏了基于知识图谱的RAG?对在不完整知识下推理的基准测试和经验洞察
机构 * University of Oslo(奥斯陆大学) ; Bosch Center for AI(博世人工智能中心) ; University of Stuttgart(斯图加特大学) ; Amazon(亚马逊公司) ; University of Oxford(牛津大学) ; The University of Manchester(曼彻斯特大学) ; University of Southampton(南安普顿大学)
AI总结 本文提出BRINK基准测试,揭示了当前KG-RAG方法在知识不完整时推理能力有限,依赖内部记忆且泛化能力各异。
Comments Accepted as a main conference paper at EACL 2026