Reinforcement Learning from Human Feedback : LLM Alignment and Post-Training.

Format:

Book

Author/Creator:

Lambert, Nathan.

Language:

English

Subjects (All):

Reinforcement learning.

Machine learning.

Human-computer interaction.

Physical Description:

1 online resource (287 pages)

Edition:

1st ed.

Place of Publication:

New York : Manning Publications Co. LLC, 2026.

Summary:

This is the authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. In this book, author Nathan Lambert blends diverse perspectives from fields like philosophy and economics with the core mathematics and computer science of RLHF to provide a practical guide you can use to apply RLHF to your models.

Contents:

Reinforcement Learning from Human Feedback

copyright

contents

foreword

preface

acknowledgments

about this book

about the author

about the cover illustration

Part 1. Overview

1 Introduction

2 A tiny history of RLHF

3 Training overview

Part 2. Core training methods

4 Instruction fine-tuning

5 Reward modeling

6 Reinforcement learning

7 Reasoning and inference-time scaling

8 Direct-alignment algorithms

9 Rejection sampling

Part 3. Data and preferences

10 The nature of preferences

11 Preference data

12 Synthetic data

Part 4. Applications and advanced topics

13 Tool use and function calling

14 Over-optimization

15 Regularization

16 Evaluation

17 Crafting model character and products

A. Definitions

B. Beyond "just style"

C. Practical issues

references.

Notes:

Description based upon print version of record.

Description based on publisher supplied metadata and other sources.

Other Format:

Print version: Lambert, Nathan Reinforcement Learning from Human Feedback

ISBN:

9781638358152

OCLC:

1610751099