Knowledge Graphs and Large Language Models

[Update 2025 en vertaling volgt spoedig]

In the past decade the concept of a knowledge graph has emerged as a pivotal framework for managing and utilizing interconnected data and information. Stemming from Google’s proclamation that shifted the focus from searching for strings to understanding entities and relationships, the term encapsulates a network of interconnected entities and concepts that facilitates semantic data integration, sharing, and utilization within organizations. At the same time, the advent of Large Language Models (LLMs) has revolutionized the field of natural language processing and artificial intelligence. These models, exemplified by architectures like GPT-4, have the capability to comprehend and generate human-like text on an unprecedented scale. By leveraging vast amounts of pre-existing linguistic data, LLMs excel in tasks such as language translation, text completion, and even creative content generation.

The synergy between knowledge graphs and LLMs represents a powerful combination that can significantly enhance various stages of knowledge graph development, such as schema design, knowledge acquisition and quality control, while reducing LLMs hallucinations and improving their accuracy, reliability, and explainability.

This 2-day course is designed to equip participants with a thorough comprehension of the synergistic potential between knowledge graphs and LLMs. Through a mix of theory and practice, the students will explore all the necessary steps for initiating and executing a knowledge graph development project, receiving practical guidance on the effective utilization of LLMs at different stages of the process. The course will also cover techniques by which knowledge graphs can be used to augment the accuracy, reliability, and explainability of LLMs.

Learning Objectives

• Decide whether a knowledge graph is a proper solution for your data challenges, and specify its desired characteristics.
• Understand the key factors determining the feasibility and viability of implementing a knowledge graph in an organization, and craft a proper development strategy
• Design a knowledge graph’s schema in a way that makes the rest of its development much easier
• Apply state-of-the-art tools and methods to (semi-)automatically populate a knowledge graph from diverse data sources.
• Implement mechanisms to assess and improve the quality of a knowledge graph
• Design and implement a knowledge graph evolution and governance strategy.
• Use LLMs to enhance all the steps of developing a knowledge graph
• Use knowledge graphs to ground LLMs and make them more accurate and reliable

Who is it for

• Data practitioners: Aspiring or practicing data scientists, data engineers or data analysts, seeking to deepen their understanding of knowledge graphs and LLMs, their implementation, and the technical intricacies involved.
• Technology Leaders: Architects, CTOs , and IT professionals exploring or leading initiatives involving data integration, semantic technologies, and generative AI
• Business Executives and Managers: Leaders and decision-makers responsible for overseeing data strategies, innovation, and organizational transformation, aiming to comprehend the strategic implications and business value derived from knowledge graph initiatives.