chapter two

2 Intelligent systems: A hybrid approach

 

This chapter covers

  • Design concepts and architecture for intelligent advisor systems
  • How hybrid systems use the complementary strengths of KGs and LLMs
  • Combining KGs and LLMs in intelligent advisor systems

This chapter explores the foundational concepts behind intelligence and intelligent behavior. At the core of our discussion lies the application of knowledge graphs (KGs) and large language models (LLMs) to solve highly complex problems by combining existing knowledge and context with reasoning and natural language understanding capabilities to build intelligent systems.

To make informed decisions about the trustworthiness and safety of intelligent systems for critical applications, we must understand how these systems operate internally, avoiding attributing capacities they lack while using their genuine capabilities. By dissecting the functioning of these systems, we can better understand their limitations and take advantage of their potential.

2.1 What is intelligence?

What is intelligence? It is the ability to acquire and apply knowledge: to learn from experience, solve problems, and interact with the environment. This natural process, honed by evolution, gives humans a competitive edge over other species. Humans do this effortlessly and unconsciously, but to design an intelligent system and a detailed structure for each element, we must dissect these processes by breaking down the various tasks and components.

2.2 Designing an intelligent system

2.2.1 What is an intelligent system?

2.2.2 Categories of intelligent systems

2.2.3 Characteristics of an intelligent system

2.3 Knowledge acquisition and representation

2.4 Reasoning

2.5 Reasoning engines

2.5.1 Limitations of a pure deductive reasoning engine

2.5.2 Using inductive reasoning and ML

2.5.3 The role of LLMs in the reasoning engine

2.6 A KG approach to IASs

Summary