Panos Alexopoulos
Panos Alexopoulos is a semantic technologies expert with nearly two decades of experience in knowledge graphs, ontology engineering, and data semantics. As of April 2025, he serves as Lead Semantic Data & AI Solutions at Triply, a semantic data integration company, after nine years as Head of Ontology at Textkernel in Amsterdam, where he led the development of a large cross-lingual knowledge graph in the HR and recruitment domain.
Panos holds a PhD in Knowledge Engineering and Management from the National Technical University of Athens and he is the author of Semantic Modeling for Data: Avoiding Pitfalls and Breaking Dilemmas (O'Reilly, 2020), a practical guide for building high-quality semantic data models. He is also also a seasoned educator, delivering training programs on topics like knowledge graphs and large language models.
Session
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances large language models (LLMs) by grounding their responses in structured knowledge graphs, offering more accurate, domain-specific, and explainable outputs. However, many of the graphs used in these pipelines are automatically generated or loosely assembled, and often lack the semantic structure, consistency, and clarity required for reliable grounding. The result is misleading retrieval, vague or incomplete answers, and hallucinations that are difficult to trace or fix.
This hands-on tutorial introduces a practical approach to evaluating and improving knowledge graph quality in GraphRAG applications. We’ll explore common failure patterns, walk through real-world examples, and share a reusable checklist of features that make a graph “AI-ready.” Participants will learn methods for identifying gaps, inconsistencies, and modeling issues that prevent knowledge graphs from effectively supporting LLMs, and apply simple fixes to improve grounding and retrieval performance in their own projects.