A continuaciónSiguiente guía
Modelado de recompensas de Bradley-Terry
Fundamentos
GUÍA de IA en idiomas
A reward model maps a prompt and response to a scalar score intended to approximate preference or another objective.
Escuche esta guíaNarrado por IA · ~2 min
It is a learned proxy, not a direct measure of human values.
In RLHF-style pipelines, a reward model is often trained on human comparisons of model outputs. A pairwise preference loss encourages the preferred response to score above the rejected response. At inference, best-of-N may sample responses and select the highest-scoring candidate. Optimizing a proxy can lead to reward hacking when the score is imperfect. InstructGPT collected human rankings of four to nine model responses for a prompt and converted those rankings into pairwise preferences for reward-model training. A common Bradley–Terry preference model converts differences between scalar response scores into preference probabilities, and the pairwise loss trains preferred responses to score higher. A common reward-model implementation uses a scalar sequence-scoring head, though architectures vary. Ensembles may reveal scorer disagreement but cannot remove shared model errors or guarantee against reward hacking.
Train from pairwise response rankings.
Use scores to rank candidate responses in best-of-N selection.
Test reward predictions on held-out comparisons.
Inspect for outputs that score highly but violate the intended behavior.
Reward models remain useful components of some alignment pipelines, but require ongoing evaluation and safeguards against optimizing unintended behaviors.
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
A reward model maps a prompt and response to a scalar score intended to approximate preference or another objective. It is a learned proxy, not a direct measure of human values.
Un modelo de recompensa asigna un mensaje y una respuesta a un número escalar que representa la calidad predicha o la preferencia humana.
InstructGPT labelers ranked sets of four to nine model outputs for a prompt; the rankings were converted into pairwise comparisons for reward-model training. This is specific to that paper’s procedure.
In the Bradley–Terry model, scalar-score differences parameterize the probability that one response is preferred to another, and the pairwise loss trains scores accordingly. These scores are not automatically calibrated measures of quality.
El hackeo de recompensas ocurre cuando el modelo encuentra atajos (como longitud excesiva o halagos) que el modelo de recompensa imperfecto califica altamente pero que los humanos no calificarían.
In a common reward-model setup, a language-model backbone is adapted with a scalar scoring head that produces one score for a prompt-response sequence. This describes that setup, not every reward-model architecture.
sigue aprendiendo
Más guías seleccionadas para este tema.
A continuaciónSiguiente guía
Modelado de recompensas de Bradley-Terry
Fundamentos