Unsupervised PRMs derived from LLM probabilities achieve up to 15% better error detection than LLM judges and match supervised PRMs in verification and RL tasks.
Figure D3: When training with uPRM-SFT, policy learns to hack the reward by generating the complete solution in a single step
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised Process Reward Models
Unsupervised PRMs derived from LLM probabilities achieve up to 15% better error detection than LLM judges and match supervised PRMs in verification and RL tasks.