AI engineering glossary · LLM training alignment
What is RLAIF (Reinforcement learning from AI feedback)?
Reinforcement learning from AI feedback (also called RLAIF): A variant of RLHF where the preference labels come from another AI model, guided by written criteria, instead of from human annotators. It scales cheaply and speeds up iteration, but inherits the judging model's biases.
Reinforcement learning from AI feedback: an example
A strong model compares two answers to 100,000 prompts using a rubric on politeness and accuracy, producing preference labels for training.
Related terms
More LLM training alignment terms
- Reinforcement learning from human feedback
- Reinforcement learning with verifiable rewards
- Rejection sampling fine-tuning
- Reward hacking
- Reward model
- Safety fine-tuning
- Scalable oversight
- Scaling laws
Where you learn it
Reinforcement learning from AI feedback is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.