Hyeonbin Hwang, Doyoung Kim, Seungone Kim, Seonghyeon Ye, Minjoon Seo. Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards. In Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen, editors, Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024. pages 1444-1466, Association for Computational Linguistics, 2024. [doi]
@inproceedings{HwangKKYS24,
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},
url = {https://aclanthology.org/2024.findings-emnlp.78},
researchr = {https://researchr.org/publication/HwangKKYS24},
cites = {0},
citedby = {0},
pages = {1444-1466},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024},
editor = {Yaser Al-Onaizan and Mohit Bansal and Yun-Nung Chen},
publisher = {Association for Computational Linguistics},
isbn = {979-8-89176-168-1},
}