How Models Learn

RLHF

Reinforcement learning from human feedback: fine-tuning a model to earn higher scores from a reward model trained on human preferences.

The whole pipeline is called reinforcement learning from human feedback, or RLHF.
From Instruction tuning and RLHF, step “Step 3: reinforcement learning from human feedback”

See it in action

Try rlhf hands-on in the lesson Instruction tuning and RLHF, part of the How AI assistants work course.

Open the lesson