Add two relevant papers

[Wangpeiyi9979]

Hi, thanks for your excellent survey.

Please consider adding two relevant papers to your repository and paper:

[1] Title: Making Large Language Models Better Reasoners with Alignment
Link: https://arxiv.org/pdf/2309.02144.pdf

This paper proposes a constrained preference alignment method to improve the reasoning ability of LLMs.

[2] Math-Shepherd: A Label-Free Step-by-Step Verifier for LLMs in Mathematical Reasoning
Link: https://arxiv.org/pdf/2312.08935.pdf
This paper proposes a framework to automatical construct the training dataset of process reward models.

Thank you for your consideration. 😊

[chuanyang-Zheng]

Thank you very much for your notice. We have added the two papers to the survey. And we will further notice you after the next round paper update on arxiv.

If there are any questions, please let us know.

Again, thank you very much for your attention to our work, and thank you for your notice.

[Wangpeiyi9979]

Thanks!

[chuanyang-Zheng]

The update version is here. https://arxiv.org/abs/2312.11562

If there are any questions, please let us know.

Again, thank you very much for your attention to our work, and thank you for your notice.