A hierarchical process reward model that classifies math and consistency errors before scoring steps achieves the best PRMBench result among discriminative PRMs and improves reward-guided math search.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision
A hierarchical process reward model that classifies math and consistency errors before scoring steps achieves the best PRMBench result among discriminative PRMs and improves reward-guided math search.