1 Understanding reasoning models
This chapter covers
- What "reasoning" means specifically in the context of LLMs
- How reasoning differs from pattern matching
- The conventional pre-training and post-training stages of LLMs
- Key approaches to improving reasoning abilities in LLMs
- Why building reasoning models from scratch can improve our understanding of their strengths, limitations, and practical trade-offs
Welcome to the next stage of large language models (LLMs): reasoning. LLMs have transformed how we process and generate text, but their success has been largely driven by statistical pattern recognition. However, new advances in reasoning methodologies now enable LLMs to tackle more complex tasks, such as solving logical puzzles and advanced math problems involving multi-step arithmetic. Understanding these methodologies is the central focus of this book.
This book teaches the inner workings of those LLM reasoning methods through a hands-on, code-first approach. As the title says, you will be creating a reasoning LLM from scratch. By the end of the book, you will understand how reasoning models work and be equipped to design, prototype, and evaluate the main methods for improving reasoning in LLMs.