Windy0822/PQM

Introduction

We present a new framework for PRM by framing it as a $Q$-value ranking problem, providing a theoretical basis for reward modeling that captures inter-dependencies among reasoning states. We also show that prior classification-based PRM can be cast as a special case under our framework. We validate its effectiveness through comprehensive experiments and ablation studies on a wide range of sampling policies, LLM backbones, and different test sets.

Checkpoints & Evaluation Data

We upload the sampling corpus of three policies to folder ./eval_data of current repository.

The checkpoints are model.safetensors in ./zeta-2 and ./zeta-4, corresponding to the two hyperparameter settings in our main experiments.

You can download them by huggingface-cli download Windy0822/PQM <filename> --local-dir <local path>