Addition Request - Paper on Improving Reasoning of Large Language Models with Alignment

[Wangpeiyi9979]

Hi, thanks for your excellent survey.

We recently proposed a new ranking strategy to align large language models (LLMs) to enhance their reasoning ability.
We also delve deeply into recent ranking-based alignment methods, such as DPO, RRHF, and PRO, and provide some analyses.

Here are the details of our work:

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

We kindly request that you consider adding our work to this repository and the survey.
Thank you for your time and consideration. 😊

[GaryYufei]

Thanks for sharing this great work with us. I have just added your paper into repo (see https://github.com/GaryYufei/AlignLLMHumanSurvey#rank-based-training), which will be incorporated into our next version of this survey!

[Wangpeiyi9979]

Thanks!