S3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners

Cite

Text

Yan et al. "S3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I24.34749

Markdown

[Yan et al. "S3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/yan2025aaai-s/) doi:10.1609/AAAI.V39I24.34749

BibTeX

@inproceedings{yan2025aaai-s,
  title     = {{S3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners}},
  author    = {Yan, Yuchen and Jiang, Jin and Liu, Yang and Cao, Yixin and Xu, Xin and Zhang, Mengdi and Cai, Xunliang and Shao, Jian},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {25588-25596},
  doi       = {10.1609/AAAI.V39I24.34749},
  url       = {https://mlanthology.org/aaai/2025/yan2025aaai-s/}
}