@inproceedings{zheng-etal-2025-logidynamics,
    title = "{L}ogi{D}ynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in {LLM} Reasoning",
    author = "Zheng, Tianshi  and
      Jiayang, Cheng  and
      Li, Chunyang  and
      Shi, Haochen  and
      Wang, Zihao  and
      Bai, Jiaxin  and
      Song, Yangqiu  and
      Wong, Ginny  and
      See, Simon",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1045/",
    pages = "20721--20742",
    ISBN = "979-8-89176-332-6",
    abstract = "Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning, making the strategic optimization of these approaches critical for advancing their capabilities. This paper systematically investigate the **comparative dynamics** of inductive (System 1) versus abductive/deductive (System 2) inference in LLMs. We utilize a controlled analogical reasoning environment, varying modality (textual, visual, symbolic), difficulty, and task format (MCQ / free-text). Our analysis reveals System 2 pipelines generally excel, particularly in visual/symbolic modalities and harder tasks, while System 1 is competitive for textual and easier problems. Crucially, task format significantly influences their relative advantage, with System 1 sometimes outperforming System 2 in free-text rule-execution. These core findings generalize to broader in-context learning. Furthermore, we demonstrate that advanced System 2 strategies like hypothesis selection and iterative refinement can substantially scale LLM reasoning. This study offers foundational insights and actionable guidelines for strategically deploying logical inference to enhance LLM reasoning."
}