Concept

Beam search

Beam search, also referred to as beam decoding, is an algorithm that extends the greedy search approach by exploring multiple potential paths simultaneously. Rather than committing to the single most probable token at each generation step, beam search retains a predetermined number of the best candidate sequences, a parameter known as the beam width. This strategy helps mitigate the problem of high-quality sequences being discarded too early in the generation process.

Image 0

0

1

Updated 2026-05-06

Tags

Data Science

Foundations of Large Language Models Course

Computing Sciences

Ch.5 Inference - Foundations of Large Language Models

Foundations of Large Language Models

Related