In today's data-driven landscape, the concept of a knowledge graph has emerged as a pivotal framework for managing and utilising 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 utilisation within organisations.

At the same time, the advent of Large Language Models (LLMs) has revolutionised 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 eliminating LLMs hallucinations and improving their accuracy, reliability, and explainability.

This 2-day online course is designed to equip participants with a thorough comprehension of the synergistic potential between knowledge graphs and LLMs. Throughout the program, participants will explore fundamental steps for initiating and executing a knowledge graph development project, receiving practical guidance on the effective utilisation of LLMs at different stages of the process. The course will also focus on empowering participants to strategically employ knowledge graphs to augment the accuracy, reliability, and explainability of Large Language Models.

The course consists of 8 modules:

Module 1 – Understanding knowledge graphs and their relation with LLMs”

• Clarification of the knowledge graph concept
• What are knowledge graphs and why would you want to build one
• Key factors influencing the ease or difficulty of building a knowledge graph
• Large Language Models (LLMs) and their interplay with knowledge graphs
• Knowledge graph development lifecycle

Module 2 – Crafting a knowledge graph strategy

• Exploring 5 key questions that are essential to answer before initiating knowledge graph development
• How to answer these questions and craft a development strategy

Module 3 – Specifying the knowledge graph:

• Typical knowledge graph specification
• Use of competency questions for gap analysis between organisational knowledge capabilities and needs
• Scoping and prioritising knowledge graph features and content

Module 4 – Designing the knowledge graph schema

• Building elements of a knowledge graph
• Knowledge graph schema design using Semantic Web languages (RDF, OWL, SKOS, SHACL) and Labeled Property Graphs.
• Conceptual modeling best practices, dilemmas, and pitfalls
• Addressing uncertainty and vagueness
• Using LLMs in schema design: what works and what doesn’t

Module 5 – Populating the knowledge graph

• Understanding and defining knowledge graph population tasks such as entity and relation extraction
• Evaluating and selecting data sources and population tools
• Designing population strategies and pipelines.
• LLMs as knowledge providers and knowledge miners - what works and what doesn’t

Module 6 – Managing knowledge graph quality:

• Knowledge graph quality dimensions, metrics, and trade-offs.
• Typical quality problems and debugging methods
• Detecting and correct quality problems in knowledge graphs 
• Crafting a quality management strategy

Module 7 – Applying knowledge graphs:

• Typical knowledge graph applications
• Developing analytics solutions with knowledge graphs
• Using knowledge graphs to ground Large Language Models

Module 8 – Maintaining and evolving knowledge graphs:

• Addressing the challenge of knowledge graph maintenance and evolution
• Detecting, measuring, and monitoring concept drift
• Crafting a knowledge graph governance strategy.

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.