Glossary · Signal and resolution
Best-of-N
Generate several candidates and select by evaluator score. It introduces extreme-selection distribution shift toward the evaluator's tail.
Defined in
Handbook · Validity under pressureAdaptive validityAccuracy before any optimization is not the question. How evaluator error grows under best-of-N and training, and how to measure an exploitability curve.Where it comes up
- LLM judges in practiceHandbook · Instrument
- Use regimes: same judge, four jobsHandbook · Regime
- Exposure, modification, and accessHandbook · Regime
- Evaluators inside training loopsHandbook · Regime
- A: Mathematical reasoningHandbook · Case studies
- Notation and formula cardHandbook · Reference