@misc{yue2023large,
title={Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoning},
author={Murong Yue and Jie Zhao and Min Zhang and Liang Du and Ziyu Yao},
year={2023},
eprint={2310.03094},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
This paper promise price reduction up to 40% in complex tasks.