@inproceedings{jiang-etal-2025-logicpro,
title = "{L}ogic{P}ro: Improving Complex Logical Reasoning via Program-Guided Learning",
author = "Jiang, Jin and
Yan, Yuchen and
Liu, Yang and
Wang, Jianing and
Peng, Shuai and
Cai, Xunliang and
Cao, Yixin and
Zhang, Mengdi and
Gao, Liangcai",
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://aclanthology.org/2025.acl-long.1270/",
doi = "10.18653/v1/2025.acl-long.1270",
pages = "26200--26218",
ISBN = "979-8-89176-251-0",
abstract = "In this paper, we propose a new data synthesis method called \textbf{LogicPro}, which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize Complex Logical Reasoning data in text format. First, we synthesize complex reasoning problems through source algorithm problems and test cases. Then, standard answers and intermediate variable outputs are obtained for each problem based on standard python solutions and test cases. Finally, with the guidance of code intermediate variables, we synthesize the text reasoning process for each reasoning problems. Through this method, we can synthesize data that is difficult, scalable, effective, and comes with golden standard answers and high-quality reasoning processes. As a result, with our 540K synthesized dataset constructed solely from 2,360 algorithm problems, our approach achieves significant improvements in multiple models for the datasets \textit{BBH{\textasciicircum}27}, \textit{LogicBench}, \textit{DROP}, \textit{AR-LSAT}, and \textit{GSM8K}, etc. outperforming a wide range of existing reasoning datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2025-logicpro">
<titleInfo>
<title>LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xunliang</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengdi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangcai</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>In this paper, we propose a new data synthesis method called LogicPro, which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize Complex Logical Reasoning data in text format. First, we synthesize complex reasoning problems through source algorithm problems and test cases. Then, standard answers and intermediate variable outputs are obtained for each problem based on standard python solutions and test cases. Finally, with the guidance of code intermediate variables, we synthesize the text reasoning process for each reasoning problems. Through this method, we can synthesize data that is difficult, scalable, effective, and comes with golden standard answers and high-quality reasoning processes. As a result, with our 540K synthesized dataset constructed solely from 2,360 algorithm problems, our approach achieves significant improvements in multiple models for the datasets BBH⌃27, LogicBench, DROP, AR-LSAT, and GSM8K, etc. outperforming a wide range of existing reasoning datasets.</abstract>
<identifier type="citekey">jiang-etal-2025-logicpro</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1270</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1270/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>26200</start>
<end>26218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
%A Jiang, Jin
%A Yan, Yuchen
%A Liu, Yang
%A Wang, Jianing
%A Peng, Shuai
%A Cai, Xunliang
%A Cao, Yixin
%A Zhang, Mengdi
%A Gao, Liangcai
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F jiang-etal-2025-logicpro
%X In this paper, we propose a new data synthesis method called LogicPro, which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize Complex Logical Reasoning data in text format. First, we synthesize complex reasoning problems through source algorithm problems and test cases. Then, standard answers and intermediate variable outputs are obtained for each problem based on standard python solutions and test cases. Finally, with the guidance of code intermediate variables, we synthesize the text reasoning process for each reasoning problems. Through this method, we can synthesize data that is difficult, scalable, effective, and comes with golden standard answers and high-quality reasoning processes. As a result, with our 540K synthesized dataset constructed solely from 2,360 algorithm problems, our approach achieves significant improvements in multiple models for the datasets BBH⌃27, LogicBench, DROP, AR-LSAT, and GSM8K, etc. outperforming a wide range of existing reasoning datasets.
%R 10.18653/v1/2025.acl-long.1270
%U https://aclanthology.org/2025.acl-long.1270/
%U https://doi.org/10.18653/v1/2025.acl-long.1270
%P 26200-26218
Markdown (Informal)
[LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning](https://aclanthology.org/2025.acl-long.1270/) (Jiang et al., ACL 2025)
ACL
- Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, and Liangcai Gao. 2025. LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 26200–26218, Vienna, Austria. Association for Computational Linguistics.