LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Tianshi, Cheng, Jiayang, Li, Chunyang, Shi, Haochen, Wang, Zihao, Bai, Jiaxin, Song, Yangqiu, Wong, Ginny Y., See, Simon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911158645030912
author Zheng, Tianshi
Cheng, Jiayang
Li, Chunyang
Shi, Haochen
Wang, Zihao
Bai, Jiaxin
Song, Yangqiu
Wong, Ginny Y.
See, Simon
author_facet Zheng, Tianshi
Cheng, Jiayang
Li, Chunyang
Shi, Haochen
Wang, Zihao
Bai, Jiaxin
Song, Yangqiu
Wong, Ginny Y.
See, Simon
contents 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. Resources are available at https://github.com/HKUST-KnowComp/LogiDynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11176
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
Zheng, Tianshi
Cheng, Jiayang
Li, Chunyang
Shi, Haochen
Wang, Zihao
Bai, Jiaxin
Song, Yangqiu
Wong, Ginny Y.
See, Simon
Computation and Language
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. Resources are available at https://github.com/HKUST-KnowComp/LogiDynamics.
title LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
topic Computation and Language
url https://arxiv.org/abs/2502.11176