A continuaciónSiguiente guía
Temperatura y muestreo
Idioma IA
GUÍA de IA en idiomas
Best-of-N is an inference-time selection method: sample multiple outputs and use a scorer or verifier to choose one.
Escuche esta guíaNarrado por IA · ~2 min
It can improve results when the model sometimes produces a good candidate and the scorer identifies it reliably. More samples cost more generation and can amplify errors in an imperfect scorer.
Best-of-N samples N candidate responses from a model and returns the one with the highest score under a reward model, verifier, or heuristic. Self-consistency is a special case that aggregates final answers by majority vote. If each independent sample has probability p of success and a perfect verifier can recognize success, the chance at least one candidate is correct is 1−(1−p)^N. Real outputs are not necessarily independent and real scorers are imperfect. Research on reward-model overoptimization finds that optimizing against a proxy can eventually reduce gold-standard performance, including in best-of-N selection.
Sampling several math solutions and selecting one that passes a verifier
Generating code candidates and ranking them with unit-test results
Using majority vote when multiple reasoning chains reach the same answer
Comparing quality gains against the additional generated tokens and scorer cost
Inference-time scaling research studies adaptive sample counts, verifiers, and reward-model calibration. The right N depends on the task, sample quality, scorer reliability, and compute budget. Evaluations should report both the selected-answer metric and the added generation/scoring cost.
Boletín gratuito
Tres noticias verificadas sobre IA cada mañana de lunes a viernes, explicadas con claridad. Gratis para siempre y sin anuncios.
Un correo cada día laborable. Date de baja con un clic. Nunca vendemos ni compartimos tu dirección.
Ponte a prueba
Corrección inmediata en cada respuesta y un certificado para compartir, con un ID verificable, cuando apruebas un curso.
Apoya la educación gratuita sobre IA. AI Understanding es una organización sin fines de lucro 501(c)(3): sin anuncios ni muros de pago, nunca. Hacer una donación
Best-of-N is an inference-time selection method: sample multiple outputs and use a scorer or verifier to choose one. It can improve results when the model sometimes produces a good candidate and the scorer identifies it reliably. More samples cost more generation and can amplify errors in an imperfect scorer.
Best-of-N extrae múltiples respuestas de candidatos y luego las reclasifica, devolviendo la de mayor puntuación.
More candidates help only if a good answer sometimes appears and the scorer can recognize it; neither condition is guaranteed.
La selección es tan buena como el reclasificador; un anotador débil o sesgado puede elegir respuestas incorrectas.
Research measures reward-model overoptimization in best-of-N: selecting extreme proxy scores can eventually lower gold-reward performance.
La autoconsistencia toma muestras de muchas cadenas de razonamiento y selecciona la respuesta final en la que la mayoría de las cadenas están de acuerdo.
sigue aprendiendo
Más guías seleccionadas para este tema.
A continuaciónSiguiente guía
Temperatura y muestreo
Idioma IA