Introduction to Large Language Models (LLMs)

Abstract

This introductory book explains the scientific and engineering principles that underpin modern Large Language Models (LLMs). It is intentionally technology-neutral: commercial systems such as ChatGPT are presented only as examples illustrating broader concepts rather than as the subject of the book. The primary objective of this book is to provide readers with the conceptual foundation required to understand how modern language models work. It is intended for university students, in particular students of Information Systems, educators, software professionals, researchers, technical managers, and all readers who wish to understand LLMs beyond their user interfaces. Artificial Intelligence has undergone several waves of development. The current wave is driven by large datasets, powerful computing platforms, and deep neural networks. Among the most influential outcomes of this evolution are Large Language Models (LLMs). This book focuses on the enduring scientific principles shared by modern LLMs rather than on any specific commercial implementation.