@inproceedings{jang-etal-2025-verbosity,
    title = "Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning",
    author = "Jang, Joonwon  and
      Kim, Jaehee  and
      Kweon, Wonbin  and
      Lee, Seonghyeon  and
      Yu, Hwanjo",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.1068/",
    pages = "20769--20784",
    ISBN = "979-8-89176-256-5",
    abstract = "Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality across a wide range of complex tasks. While this approach has proven effective, it inevitably increases substantial inference costs. Previous methods adopting token-level reduction without clear criteria result in poor performance compared to models trained with complete rationale. To address this challenge, we propose a novel sentence-level rationale reduction framework leveraging likelihood-based criteria, *verbosity*, to identify and remove redundant reasoning sentences. Unlike previous approaches, our method leverages *verbosity* to selectively remove redundant reasoning sentences while preserving reasoning capabilities. Our experimental results across various reasoning tasks demonstrate that our method improves performance by an average of 7.71{\%} while reducing token generation by 19.87{\%} compared to model trained with complete reasoning paths."
}