RLHF

Reinforcement Learning from Human Feedback

Concise chapter notes with the original figures and short review questions.

Chapters 1-3

Introduction to RLHF

A compact orientation to what RLHF changes, why the field formed, and how the modern training loop fits together.

Open chapter

Chapter 4

Instruction Fine-tuning

The step that turns a base next-token model into something that reliably participates in the question-answer format.

Open chapter

Chapter 5

Reward Modeling

How human comparisons or verifier labels become a scalar signal that later training can optimize.

Open chapter

Chapter 6

Reinforcement Learning (Policy Gradients)

The main optimization family for pushing a model toward higher reward while trying not to let it drift too far from useful behavior.

Open chapter

Chapter 7

Reasoning Training & Inference-Time Scaling

Why RL surged again in the reasoning era, and how verification-driven training differs from classic preference optimization.

Open chapter

Chapter 8

Direct Alignment Algorithms

Methods like DPO that optimize preference data directly instead of fitting a separate reward model first.

Open chapter

Chapter 9

Rejection Sampling

A simple but powerful recipe: generate many candidates, score them, keep the best, and fine-tune on the survivors.

Open chapter

Chapter 10

The Nature of Preferences

The conceptual chapter: what a preference really is, why RLHF needs one, and why the target is philosophically messier than it first sounds.

Open chapter

Chapter 11

Preference Data

How preference labels are actually gathered, what interfaces shape the labels, and why the collection process itself introduces bias.

Open chapter

Chapter 12

Synthetic Data & Distillation

How models increasingly learn from other models, and why synthetic feedback now sits at the center of many post-training pipelines.

Open chapter

Chapter 13

Tool Use & Function Calling

How assistant behavior expands once the model can call external tools instead of only emitting plain language.

Open chapter

Chapter 14

Over Optimization

What it looks like when the model gets better at the proxy objective faster than it gets better at what people actually want.

Open chapter

Chapter 15

Regularization

The family of constraints that keep optimization productive instead of letting it destroy useful prior behavior.

Open chapter

Chapter 16

Evaluation

How to tell whether a post-training method actually helped, and why evaluation quality often lags behind optimization quality.

Open chapter

Chapter 17

Product, UX, and Model Character

Why post-training is not only about correctness or safety, but also about shaping the assistant’s persona and fit to a product.

Open chapter