Mai departeUrmătorul ghid
Bradley-Terry Reward Modeling
Fundamentele
GHID AI limbaj
A reward model maps a prompt and response to a scalar score intended to approximate preference or another objective.
Ascultă acest ghidNarativ AI · ~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.
Buletin gratuit
Trei povești AI verificate în fiecare dimineață de zi lucrătoare, scrise în engleză simplă. Gratuit pentru totdeauna, fără reclame.
Un e-mail în fiecare zi lucrătoare. Dezabonare cu un singur clic. Nu vindem niciodată și nu împărtășim adresa ta.
Testează-te
Feedback instantaneu la fiecare răspuns și un certificat partajabil cu un ID verificabil după ce parcurgi un curs.
Susține educația AI gratuită. AI Understanding este o organizație nonprofit 501(c)(3) — fără reclame, fără barieră de plată, pentru totdeauna. Fă o donație
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 model de recompensă mapează un prompt și un răspuns la un număr scalar care reprezintă calitatea prezisă sau preferința umană.
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.
Hackingul de recompense are loc atunci când modelul găsește scurtături (cum ar fi lungimea excesivă sau lingușirea) pe care modelul de recompensă imperfect le evaluează foarte mult, dar oamenii nu le-ar face.
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.
Continuați să învățați
Mai multe ghiduri alese pentru acest subiect
Mai departeUrmătorul ghid
Bradley-Terry Reward Modeling
Fundamentele