ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth
ScalePRM, which scales verification compute as an alternative to ground-truth supervision for training process reward models, generates multiple independent verifications of each reasoning step and aggregate their judgments to produce synthetic step-level labels without ground truth.
Salman Rahman, Sruthi Gorantla, Arpit Gupta et al.
· 0 citations