2 Intelligent systems: a hybrid approach
This chapter covers
- Key design concepts and architecture for intelligent advisor systems
- How hybrid systems leverage the complementary strengths of KGs and LLMs
- Integration strategies for combining KGs and LLMs in intelligent advisor systems
In this chapter, we embark on a journey to explore the foundational concepts behind intelligence and intelligent behavior, which are essential for designing effective systems for our purposes. At the core of our discussion lies the application of knowledge graphs (KGs) and large language models (LLMs) to solve highly complex problems, like helping physicians heal patients, aiding law enforcement analysts in fighting crime, assisting credit card providers in combating fraud and many others. These types of problems require the combination of existing knowledge and context with reasoning capabilities, to build proper intelligent systems.
To make informed decisions about the trustworthiness and safety of intelligent systems for critical applications – that are the type of systems we would like to design and implement in this book –, we must know how these systems operate internally, avoiding the attribution of capacities they lack while leveraging their genuine capabilities. Understanding the inner workings of intelligent systems is crucial for AI practitioners. By dissecting the functioning of these systems, we can better understand their limitations and leverage their potential.