Training technique where a model is fine-tuned using human feedback on the quality of its responses, training a reward model that guides the main model toward outputs more aligned with human preferences.
In AIF-C01 (Domain 3) it comes up as part of data preparation for fine-tuning and model alignment. It's the technique large commercial LLMs use to become more helpful and safe after initial pre-training.
RLHF (Reinforcement Learning from Human Feedback) is a concept that can show up on the exam. Check the full guide to see it in context.