{"slug": "graph-databases-make-vector-rag-better", "title": "Graph databases make vector RAG better", "summary": "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.", "body_md": "# Graph databases make vector RAG better\n\nGraph 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.\n\nIt 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.\n\nThe 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.”\n\nThey 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?”\n\nAnswering 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.”\n\nThey asked the question to three kinds of LLM and evaluated the results:\n\n1. 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).\n\n2. Simple vector RAG\n\n3. Zero-shot LLM with no RAG\n\nThe 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).”\n\nBut 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.”\n\nAll-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.”\n\nRead the paper for a detailed look at what's involved.", "url": "https://wpnews.pro/news/graph-databases-make-vector-rag-better", "canonical_source": "https://www.blocksandfiles.com/ai-ml/2026/07/23/graph-databases-make-vector-rag-better/5277332", "published_at": "2026-07-23 16:14:00+00:00", "updated_at": "2026-07-23 16:35:44.105724+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-agents", "ai-tools"], "entities": ["Neo4j", "arXiv", "MoNaCo", "Wikipedia"], "alternates": {"html": "https://wpnews.pro/news/graph-databases-make-vector-rag-better", "markdown": "https://wpnews.pro/news/graph-databases-make-vector-rag-better.md", "text": "https://wpnews.pro/news/graph-databases-make-vector-rag-better.txt", "jsonld": "https://wpnews.pro/news/graph-databases-make-vector-rag-better.jsonld"}}