Practice free →
HomeClaudeaifoundationsinstructgpt_rlhf › The reward model is trained on

The reward model is trained on

APairwise comparisons of model outputs
BSingle absolute scores per output
CRule-based outputs from a regex set
DHuman-written critiques of each token
Answer & Solution
Correct answer: A. Pairwise comparisons of model outputs
Labelers rank K outputs to a prompt (K is 4 to 9). All C(K,2) pairs become preference labels. The RM learns to assign higher scalar rewards to the preferred completions.
Solve this in the app — Claude practice & 24k+ MCQs →
Related questions