Process Reward Models (PRMs) trained on step-level error labels automatically annotated by formal verification tools.
-
Training Step-Level Reasoning Verifiers with Formal Verification Tools
Paper • 2505.15960 • Published • 7 -
ryokamoi/Llama-3.1-8B-FoVer-PRM
Text Generation • 8B • Updated • 5 -
ryokamoi/Qwen-2.5-7B-FoVer-PRM
Text Generation • 8B • Updated • 6 • 1 -
ryokamoi/FoVer-FormalLogic-Llama-3.1-8B
Viewer • Updated • 10.7k • 34
