Glossary · Use and training pipelines
RLHF
Reinforcement learning from human feedback: a training pipeline that consumes preference data, usually via a learned reward model and policy optimization. Not itself an evaluator family.
Defined in
Handbook · RegimeEvaluators inside training loopsRLHF is a pipeline, not an evaluator. Where the learned judge sits in RLHF, RLAIF, RLVR and DPO, and what it is exposed to.Where it comes up
- Vocabulary without category errorsHandbook · Foundations
- Inverse evaluation designHandbook · Practice