James Clarkson

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation Graph-powered AI reduces hallucinations and boosts answer accuracy A new study from the National Innovation Centre for Data has shown combining large language models with graph technology can significantly improve AI accuracy, completeness and trustworthiness. Research at a Glance - 510 complex questions tested. - 80% improvement in truthfulness versus standard vector RAG. - More than 2x increase in questions answered. - Uses automatically generated graph structures, making enterprise adoption practical.   While LLMs have rapidly transformed the way organisations access information, they remain prone to two critical weaknesses: hallucinations and omissions. Hallucinations occur when an AI system confidently generates information that is incorrect, unsupported or entirely fabricated.  Omissions happen when an AI response leaves out important facts or context needed to answer a question accurately.  In both cases, the answer can appear credible and convincing, making it difficult for users to identify mistakes. These issues can create significant risks in areas such as compliance, legal research, customer service, due diligence and knowledge management. As organisations increasingly rely on AI to analyse complex information and support decision-making, improving the accuracy, completeness and reliability of AI-generated answers has become a major focus for researchers and industry alike as otherwise, the consequences can be significant, particularly in regulated or high-stakes environments. The research suggests that adding graph-based context helps AI systems better connect information across multiple documents and entities, leading to more complete and reliable answers. Compared with a standard vector-based RAG system, the graph-enhanced approach: - Increased AI truthfulness scores by approximately 80%. - More than doubled the number of complex questions answered increasing answer rates from 29% to nearly 66%.   Findings indicate that organisations can improve AI reliability without fundamentally changing how employees interact with AI tools, instead strengthening the information retrieval process behind the scenes. Researchers evaluated three different approaches to answering 510 complex questions drawn from a recent peer-reviewed research benchmark designed to test reasoning across multiple documents and sources. The study compared: - A traditional vector-based agentic RAG system. - A graph-enhanced agentic RAG system combining semantic search with document structure-based graph tools. - A standalone LLM with no retrieval tools.   Unlike many previous approaches, the graphs used in the research were automatically generated from document structures such as article titles, sections, paragraphs and links.  This demonstrates that organisations can benefit from graph-enhanced AI without needing to invest in highly complex or manually curated knowledge graphs, making it easier for organisations to apply to internal knowledge bases, policies, reports, technical documentation and operational data.  While the researchers note that further testing across additional datasets, AI models and real-world enterprise environments will be important, the results demonstrate the potential for graph-enhanced retrieval to play a significant role in the next generation of enterprise AI systems. The study was conducted using a single benchmark dataset and one LLM reasoning model (GPT 5.4), highlighting opportunities for future research and broader validation. By NICD Neo4j arxiv.org/abs/2606.05901 #Research #GraphRAG #EmergingTech #LLM #GenAI -- Join the Conversation Subscribe to the Year of the Graph newsletter for quarterly insights on #KnowledgeGraphs, #GraphDB, Graph #Analytics, #AI, #DataScience and #SemTech . 📧 Subscribe: yearofthegraph.xyz/newslette…  💼 Sponsorship inquiries: yearofthegraph.xyz/contact/