README.md

GenRM-CoT: Data release for verification rationales

Data accompanying the paper "Generative Verifiers: Reward Modeling as Next-Token Prediction".

See our website for an overview of GenRM.

Licence

GSM8K data: Copyright (c) 2021 OpenAI, available under MIT Licence

Citations

Please cite our paper as:

@article{zhang2024genrm,
  title={Generative verifiers: Reward modeling as next-token prediction},
  author={Zhang, Lunjun and Hosseini, Arian and Bansal, Hritik and Kazemi, Mehran and Kumar, Aviral and Agarwal, Rishabh},
  journal={arXiv preprint arXiv:2408.15240},
  year={2024}
}