@inproceedings{kang-etal-2025-exploring,
title = "Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning",
author = "Kang, Jiabao and
Li, Xinye and
Xu, Liyan and
Liu, Qingbin and
Chen, Xi and
Tu, Zhiying and
Chu, Dianhui and
Sui, Dianbo",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.887/",
doi = "10.18653/v1/2025.findings-emnlp.887",
pages = "16320--16341",
ISBN = "979-8-89176-335-7",
abstract = "Deductive and inductive reasoning are fundamental components of human cognition, and in daily life, people often apply these types of reasoning unconsciously. While previous studies have extensively examined the deductive and inductive reasoning abilities of Large Language Models (LLMs) in rule-based and math-related tasks, little attention has been given to their role in procedural planning{---}{---}an area that holds considerable relevance for real-world applications. To fill this gap, we present DIRPP (Deductive and Inductive Reasoning in Procedural Planning) in this paper, a benchmark designed to assess the deductive and inductive reasoning abilities of various LLMs within the context of procedural planning. Based on the benchmark, we initially observe that LLMs demonstrate excellent deductive reasoning capabilities in procedural planning but show suboptimal performance in inductive reasoning. To enhance their inductive reasoning abilities, we further propose a novel and effective method called IMSE (Induction through Multiple Similar Examples), which enables LLMs to generate multiple similar procedural plans and then perform inductive reasoning based on these examples. Through various experiments, we find that the proposed method can significantly improve the inductive reasoning capabilities of LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kang-etal-2025-exploring">
<titleInfo>
<title>Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiabao</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinye</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingbin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiying</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dianhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dianbo</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Deductive and inductive reasoning are fundamental components of human cognition, and in daily life, people often apply these types of reasoning unconsciously. While previous studies have extensively examined the deductive and inductive reasoning abilities of Large Language Models (LLMs) in rule-based and math-related tasks, little attention has been given to their role in procedural planning——an area that holds considerable relevance for real-world applications. To fill this gap, we present DIRPP (Deductive and Inductive Reasoning in Procedural Planning) in this paper, a benchmark designed to assess the deductive and inductive reasoning abilities of various LLMs within the context of procedural planning. Based on the benchmark, we initially observe that LLMs demonstrate excellent deductive reasoning capabilities in procedural planning but show suboptimal performance in inductive reasoning. To enhance their inductive reasoning abilities, we further propose a novel and effective method called IMSE (Induction through Multiple Similar Examples), which enables LLMs to generate multiple similar procedural plans and then perform inductive reasoning based on these examples. Through various experiments, we find that the proposed method can significantly improve the inductive reasoning capabilities of LLMs.</abstract>
<identifier type="citekey">kang-etal-2025-exploring</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.887</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.887/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>16320</start>
<end>16341</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning
%A Kang, Jiabao
%A Li, Xinye
%A Xu, Liyan
%A Liu, Qingbin
%A Chen, Xi
%A Tu, Zhiying
%A Chu, Dianhui
%A Sui, Dianbo
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F kang-etal-2025-exploring
%X Deductive and inductive reasoning are fundamental components of human cognition, and in daily life, people often apply these types of reasoning unconsciously. While previous studies have extensively examined the deductive and inductive reasoning abilities of Large Language Models (LLMs) in rule-based and math-related tasks, little attention has been given to their role in procedural planning——an area that holds considerable relevance for real-world applications. To fill this gap, we present DIRPP (Deductive and Inductive Reasoning in Procedural Planning) in this paper, a benchmark designed to assess the deductive and inductive reasoning abilities of various LLMs within the context of procedural planning. Based on the benchmark, we initially observe that LLMs demonstrate excellent deductive reasoning capabilities in procedural planning but show suboptimal performance in inductive reasoning. To enhance their inductive reasoning abilities, we further propose a novel and effective method called IMSE (Induction through Multiple Similar Examples), which enables LLMs to generate multiple similar procedural plans and then perform inductive reasoning based on these examples. Through various experiments, we find that the proposed method can significantly improve the inductive reasoning capabilities of LLMs.
%R 10.18653/v1/2025.findings-emnlp.887
%U https://aclanthology.org/2025.findings-emnlp.887/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.887
%P 16320-16341
Markdown (Informal)
[Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning](https://aclanthology.org/2025.findings-emnlp.887/) (Kang et al., Findings 2025)
ACL
- Jiabao Kang, Xinye Li, Liyan Xu, Qingbin Liu, Xi Chen, Zhiying Tu, Dianhui Chu, and Dianbo Sui. 2025. Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16320–16341, Suzhou, China. Association for Computational Linguistics.