Beam Search
Keeping several candidate sequences alive and extending the best.
Resumen
Beam search expands several partial sequences at once and keeps the highest-scoring ones, rather than committing to the token chosen at each step. It solves the problem that greedy decoding can be locally optimal and globally poor. It exists as the default for translation and summarisation, and it tends to produce bland text for open-ended generation.
Grafo de tecnologías
Cómo se conecta Beam Search con el resto del stack.
Alternativas
-
Top-p Sampling
technique
Una alternativa a Beam Search · source
Comparativas
Comparativas detalladas con las alternativas anteriores.