Graph databases make vector RAG better

Neo4j says graph technology can reduce AI hallucinations, citing a June arXiv paper showing that vector+graph RAG achieved 80% higher fine-grained truthfulness and more than double the precision and recall of vector RAG alone on complex Wikipedia QA tasks from the MoNaCo benchmark.

Graph databases make vector RAG better Graph database supplier Neo4j https://www.blocksandfiles.com/ai-ml/2025/10/03/neo4j-bids-to-take-graph-technology-into-ais-mainstream/1613209 says graph tech can stop AI models and agents dreaming, hallucinating, and fabricating false answers to questions. It pointed us towards a recent academic paper; ” Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation https://arxiv.org/abs/2606.05901 " published on arXiv in June, that it says proves its point. The paper’s abstract states it explores “the idea of using a lightweight graph structure with a relatively simple graph schema, to support the RAG https://www.blocksandfiles.com/glossary/2022/02/20/rag/1610766 Retrieval-Augmented Generation subsystem via a dedicated toolset. We design an agentic system with a variety of vector https://www.blocksandfiles.com/ai-ml/2022/04/28/vector-embedding/1596580 search and graph query tools operating over a structured dataset based on a curated subset of English Wikipedia articles, and evaluate its performance on questions from MoNaCo, a challenging Wikipedia QA question answering benchmark of complex query answering tasks.” They pose a question for an LLM to answer: “Can you name all the battles between the Dutch and English in the First, Second and Third Anglo-Dutch Wars, and list the victor of each battle?” Answering this requires “a sophisticated retrieval and reasoning process. In fact, it requires multi-entity and multi-hop reasoning, and cross-document access, all at once.” They observe that: “These types of questions pose a significant challenge to current state-of-the-art LLM-based systems.” They asked the question to three kinds of LLM and evaluated the results: 1. Vector+graph RAG - using a unified vector and graph database with a series of pre-defined tools to improve retrieval from external knowledge bases KBs . 2. Simple vector RAG 3. Zero-shot LLM with no RAG The paper says: “The results shown indicate that augmenting a basic vector RAG subsystem with a simple graph-based KB and corresponding tools can significantly reduce the amount of hallucinated content” but not completely: “ the coarse truthfulness score improved from about −127 to −49 for vector+graph RAG vs zero-shot .” But it’s much better than vector RAG alone: ”We also show that, when partially correct answers are taken into account, vector+graph RAG achieves the highest score across all three evaluated scenarios; the fine-grained truthfulness score was 80 percent higher than for vector RAG. Additionally, the factual correctness results indicate that vector+graph RAG achieves more than twice the precision and recall of the system based solely on vector RAG.” All-in-all: “By increasing both precision and recall while reducing hallucinations, the proposed solution is a promising direction towards increasing trust in LLM-based QA systems.” Read the paper for a detailed look at what's involved.