Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning formats outperform a single format when generating multiple answers. However, previous works using multiple formats rely on formats labeled by humans, which could be unsuitable for all tasks and have high labeling costs. To address this issue, we adapt suitable formats to the given tasks by generating and selecting formats. We first propose how to measure the reasoning error when generating multiple answers. Then, we introduce Format-Adapter, which utilizes LLMs to generate and select suitable reasoning formats by minimizing the error measurement we present. We conduct experiments on math and commonsense reasoning tasks, where Format-Adapter achieves a 4.3% performance improvement on average over previous works, demonstrating the effectiveness.
@article{arxiv.2506.23133,
title = {Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format},
author = {Dingzirui Wang and Xuanliang Zhang and Rongyu Cao and Longxu Dou and Xianzhen Luo and Yingwei Ma and Qingfu Zhu and Wanxiang Che and Binhua Li and Fei Huang and Yongbin Li},
journal= {arXiv preprint arXiv:2506.23133},
year = {2025}
}