AI RESEARCH
The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA
arXiv CS.CL
•
ArXi:2603.14045v1 Announce Type: cross Graph-RAG systems achieve strong multi-hop question answering by indexing documents into knowledge graphs, but strong retrieval does not guarantee strong answers. Evaluating KET-RAG, a leading Graph-RAG system, on three multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA), we find that 77% to 91% of questions have the gold answer in the retrieved context, yet accuracy is only 35% to 78%, and 73% to 84% of errors are reasoning failures.