Glossary · Use and training pipelines
Bradley–Terry model
A pairwise preference model, Pr[y_w ≻ y_l | x] = σ(r(x, y_w) − r(x, y_l)), used to train reward models from comparisons. Only score differences matter: it learns a preference ordering, not a proof of quality.
Also called: Bradley-Terry
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.Related terms
- Reward model (RM)
- A learned model that predicts preference or quality, typically as a scalar or pairwise estimate, and is often optimized against.
Where it comes up
- Notation and formula cardHandbook · Reference