Glossary · Use and training pipelines
Selection (use)
3RegimeA use in which the evaluator chooses among generated candidates, as in best-of-N. It belongs to the optimize regime.
Also called: selection use
Defined in
Handbook · RegimeUse regimes: same judge, four jobsMeasure, optimize or monitor: an evaluator changes meaning when its signal enters a different loop, and signals migrate between loops.Related terms
- Best-of-N
- Generate several candidates and select by evaluator score. It introduces extreme-selection distribution shift toward the evaluator's tail.
- Use regime
- The causal role a signal plays: measure (supports inference), optimize (shapes the candidate or policy distribution), or monitor-control (detects and intervenes in deployment).