@inproceedings{cai-etal-2025-role,
    title = "The Role of Deductive and Inductive Reasoning in Large Language Models",
    author = "Cai, Chengkun  and
      Zhao, Xu  and
      Liu, Haoliang  and
      Jiang, Zhongyu  and
      Zhang, Tianfang  and
      Wu, Zongkai  and
      Hwang, Jenq-Neng  and
      Li, Lei",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.820/",
    pages = "16780--16790",
    ISBN = "979-8-89176-251-0",
    abstract = "Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a major challenge. In this paper, we propose the **Deductive and Inductive (DID)** method, a novel framework that enhances LLM reasoning by dynamically integrating both deductive and inductive reasoning approaches. Drawing from cognitive science principles, DID implements a dual-metric complexity evaluation system that combines Littlestone dimension and information entropy to precisely assess task difficulty and guide decomposition strategies. DID enables the model to progressively adapt its reasoning pathways based on problem complexity, mirroring human cognitive processes. We evaluate DID{'}s effectiveness across multiple benchmarks, including the AIW, MR-GSM8K, and our custom Holiday Puzzle dataset for temporal reasoning. Our results demonstrate great improvements in reasoning quality and solution accuracy - achieving 70.3{\%} accuracy on AIW (compared to 62.2{\%} for Tree of Thought), while maintaining lower computational costs."
}