{
  "id": "best-of-n-sampling",
  "code": "PTL-0054",
  "term": "Best-of-N Sampling",
  "aliases": [
    "rejection sampling",
    "best-of-n",
    "BoN"
  ],
  "category": "verification",
  "definition": "Best-of-N sampling generates N candidate outputs and returns the one ranked highest by a verifier, reward model, or scoring function.",
  "description": "It is the simplest form of trading inference compute for quality. Its effectiveness depends on the verifier, and optimizing too hard against an imperfect reward model can select outputs that game it.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "self-consistency",
    "process-reward-model",
    "test-time-compute-scaling"
  ],
  "introduced": null,
  "sources": [
    {
      "title": "Let's Verify Step by Step",
      "authors": "Lightman et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2305.20050"
    },
    {
      "title": "Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters",
      "authors": "Snell et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2408.03314"
    }
  ],
  "url": "https://protologue.com/t/best-of-n-sampling/",
  "citation": "Protologue. (2026). Best-of-N Sampling. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0054). https://protologue.com/t/best-of-n-sampling/"
}