@inproceedings{wang-etal-2026-format,
    title = "Format-Adapter: Improving Reasoning Capability of {LLM}s by Adapting Suitable Format",
    author = "Wang, Dingzirui  and
      Zhang, Xuanliang  and
      Cao, Rongyu  and
      Dou, Longxu  and
      Luo, Xianzhen  and
      MA, Yingwei  and
      Zhu, Qingfu  and
      Li, Binhua  and
      Huang, Fei  and
      Li, Yongbin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1124/",
    pages = "22408--22427",
    ISBN = "979-8-89176-395-1",
    abstract = "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."
}