How Large Language Models Work

Learn how large language models like GPT and Gemini work under the hood in plain English.

How Large Language Models Work translates years of expert research on Large Language Models into a readable, focused introduction to working with these amazing systems. It explains clearly how LLMs function, introduces the optimization techniques to fine-tune them, and shows how to create pipelines and processes to ensure your AI applications are efficient and error-free.

In How Large Language Models Work you will learn how to:

• Test and evaluate LLMs
• Use human feedback, supervised fine-tuning, and Retrieval augmented generation (RAG)
• Reducing the risk of bad outputs, high-stakes errors, and automation bias
• Human-computer interaction systems
• Combine LLMs with traditional ML

Purchase of the print book includes a free eBook in PDF and ePub formats from Manning Publications.

How Large Language Models Work is written by some of the best machine learning researchers at Booz Allen Hamilton, including researcher Stella Biderman, Director of AI/ML Research Drew Farris, and Director of Emerging AI Edward Raff. In clear and simple terms, these experts lay out the foundational concepts of LLMs, the technology’s opportunities and limitations, and best practices for incorporating AI into your organization.

About the book

How Large Language Models Work is an introduction to LLMs that explores OpenAI’s GPT models. The book takes you inside ChatGPT, showing how a prompt becomes text output. In clear, plain language, this illuminating book shows you when and why LLMs make errors, and how you can account for inaccuracies in your AI solutions. Once you know how LLMs work, you’ll be ready to start exploring the bigger questions of AI, such as how LLMs “think” differently that humans, how to best design LLM-powered systems that work well with human operators, and what ethical, legal, and security issues can—and will—arise from AI automation.

About the reader

Includes examples in Python. No knowledge of ML or AI systems is required.

About the author

Edward Raff is a Director of Emerging AI at Booz Allen Hamilton, where he leads the machine learning research team. He has worked in healthcare, natural language processing, computer vision, and cyber security, among fundamental AI/ML research. The author of Inside Deep Learning, Dr. Raff has over 100 published research articles at the top artificial intelligence conferences. He is the author of the Java Statistical Analysis Tool library, a Senior Member of the Association for the Advancement of Artificial Intelligence, and twice chaired the Conference on Applied Machine Learning and Information Technology and the AI for Cyber Security workshop. Dr. Raff's work has been deployed and used by anti-virus companies all over the world.

Drew Farris is a Director of AI/ML Research at Booz Allen Hamilton. He works with clients to build information retrieval, as well as machine learning and large scale data management systems, and has co-authored Booz Allen's Field Guide to Data Science, Machine Intelligence Primer and Manning Publications' Taming Text, the 2013 Jolt Award-winning book on computational text processing. He is a member of the Apache Software Foundation and has contributed to a number of open source projects including Apache Accumulo, Lucene, Mahout and Solr.

Stella Biderman is a machine learning researcher at Booz Allen Hamilton and the executive director of the non-profit research center EleutherAI. She is a leading advocate for open source artificial intelligence and has trained many of the world's most powerful open source artificial intelligence algorithms. She has a master's degree in computer science from the Georgia Institute of Technology and degrees in Mathematics and Philosophy from the University of Chicago.