PapersPapers BooksBooks LearnLearn LibraryLibrary

Sign in Sign up

Reinforcement Learning from Human Feedback

Chapter 11

Preference Data

Nathan LambertCC BY-NC-SA 4.0 Read on rlhfbook.com

Loading the chapter from rlhfbook.com…

Chapter 10The Nature of Preferences Chapter 12Synthetic Data & Distillation

From Reinforcement Learning from Human Feedback by Nathan Lambert, © 2025–2026 Nathan Lambert. The chapter text is licensed CC BY-NC-SA 4.0. Some images are third-party and not covered by that license. Shown in DailyPaper’s layout: your browser loads the text, images and links from rlhfbook.com each time, and DailyPaper keeps no copy. Read on rlhfbook.com