Название: LLM Reliability: Performance, hallucinations, accuracy, and bias (MEAP v6)
Автор: Rush Shahani
Издательство: Manning Publications
Год: 2025
Страниц: 310
Язык: английский
Формат: pdf, epub
Размер: 14.2 MB

Tested strategies to reduce hallucinations, improve performance and cost efficiency, and reduce bias or unethical behavior in your LLMs outputs.

LLM Reliability shows you exactly how to guide large language models from research prototypes to scalable, robust, and efficient production systems. From model training to maintenance, an engineer will find everything they need to work with LLMs in this one-stop guide.

This book is written for developers, engineers, and data scientists who are ready to take their knowledge of Large Language Models (LLMs) beyond theory and into real-world, production-level applications. To get the most out of this book, it helps if you have a basic understanding of Python programming and some familiarity with LLMs like OpenAI and Claude. If you’re comfortable with LLM basics like hallucinations and prompting, you’re well-prepared to jump right in. Even if you’re newer to LLMs, this book is designed to build on foundational knowledge and guide you step-by-step toward successfully deploying LLMs in production environments.

Inside LLM Reliability you’ll learn how to:
Deploy LLMs into production
Detect and reduce hallucinations
Mitigate bias
Optimize LLM performance and resource usage
Advanced prompt engineering techniques
Build intelligent agents and Retrieval-Augmented Generation

LLM Reliability is a guide to putting LLMs into production in the real world. The book bridges the gap between theory and practice. You’ll go beyond basics like prompting into advanced optimizations: intelligent agents, Retrieval Augmented Generation (RAG), and in-depth solutions for mitigating hallucinations and bias.

about the book:
LLM Reliability is a comprehensive guide to creating LLM-based apps that are faster and more accurate. It takes you from training to production and beyond into the ongoing maintenance of an LLM. In each chapter, you’ll find in-depth code samples and hands-on projects—including building a RAG-powered chatbot and an agent created with LangChain. Deploying an LLM can be costly, so you’ll love the performance optimization techniques—prompt optimization, model compression, and quantization—that make your LLMs quicker and more efficient. Throughout, real-world case studies from e-commerce, healthcare, and legal work give concrete examples of how businesses have solved some of LLMs common problems.

about the reader
For data scientists or software engineers confident in Python and NLP.