Improve mathematical reasoning in language models by automated process supervision
TL;DR
Collected lots of process supervision data to train better reward models to solve math.
BibTeX
@article{luo2024improvemathematicalreasoninglanguage,
title={Improve Mathematical Reasoning in Language Models by Automated Process Supervision},
author={Liangchen Luo and Yinxiao Liu and Rosanne Liu and Samrat Phatale and Meiqi Guo and Harsh Lara and Yunxuan Li and Lei Shu and Yun Zhu and Lei Meng and Jiao Sun and Abhinav Rastogi},
year={2024},
eprint={2406.06592},
archivePrefix={arXiv},
primaryClass={cs.CL}
title={Improve Mathematical Reasoning in Language Models by Automated Process Supervision},
author={Liangchen Luo and Yinxiao Liu and Rosanne Liu and Samrat Phatale and Meiqi Guo and Harsh Lara and Yunxuan Li and Lei Shu and Yun Zhu and Lei Meng and Jiao Sun and Abhinav Rastogi},
year={2024},
eprint={2406.06592},
archivePrefix={arXiv},
primaryClass={cs.CL}
Date
June, 2024
Links