Socratic-PRMBench tests process reward models on deliberately flawed math reasoning across six reasoning patterns and reports that current PRMs score below LLM critics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
Socratic-PRMBench tests process reward models on deliberately flawed math reasoning across six reasoning patterns and reports that current PRMs score below LLM critics.