Concept

Best-of-N Sampling

Best-of-N sampling is a method used to improve model outputs by generating multiple (N) potential solutions for a given input. From this set of N outputs, the best one is selected using a specific mechanism, such as a verifier model or an evaluation function. This technique leverages a model's ability to generate diverse responses to find a higher-quality solution than what might be produced in a single attempt.

0

1

Updated 2026-05-06

Contributors are:

Who are from:

Tags

Ch.5 Inference - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences