@article{selfexploretoavoidthepitimprovingthe,
  title = {Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards},
  author = {Hyeonbin Hwang and Doyoung Kim and Seungone Kim and Seonghyeon Ye and Minjoon Seo},
  year = {2024},
  eprint = {2404.10346},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.10346v4},
}