@inproceedings{you-etal-2024-mumath,
title = "{M}u{M}ath: Multi-perspective Data Augmentation for Mathematical Reasoning in Large Language Models",
author = "You, Weihao and
Yin, Shuo and
Zhao, Xudong and
Ji, Zhilong and
Zhong, Guoqiang and
Bai, Jinfeng",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.185",
pages = "2932--2958",
abstract = "Recently, the tool-use Large Language Models (LLMs) that integrate with external Python interpreters have significantly enhanced mathematical reasoning capabilities for open-source LLMs. However, these models fall short in demonstrating the calculation process, which compromises user-friendliness and understanding of problem-solving steps. Conversely, while tool-free methods offer a clear display of the problem-solving process, their accuracy leaves room for improvement.These tool-free methods typically employ a somewhat narrow range of augmentation techniques such as rephrasing and difficulty enhancement to boost performance. In response to this issue, we have amalgamated and further refined these strengths while broadening the scope of augmentation methods to construct a **mu**lti-perspective augmentation dataset for **math**ematics{---}termed **MuMath** ($\mu$-Math) Dataset.Subsequently, we finetune LLaMA-2 on the MuMath dataset to derive the MuMath model. Our experiments indicate that our MuMath-70B model achieves new state-of-the-art performance among tool-free methods{---}achieving 88.3{\%} on GSM8K and 34.5{\%} on MATH .We release the MuMath dataset along with its corresponding models and code for public use.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2024-mumath">
<titleInfo>
<title>MuMath: Multi-perspective Data Augmentation for Mathematical Reasoning in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weihao</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xudong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhilong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoqiang</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinfeng</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, the tool-use Large Language Models (LLMs) that integrate with external Python interpreters have significantly enhanced mathematical reasoning capabilities for open-source LLMs. However, these models fall short in demonstrating the calculation process, which compromises user-friendliness and understanding of problem-solving steps. Conversely, while tool-free methods offer a clear display of the problem-solving process, their accuracy leaves room for improvement.These tool-free methods typically employ a somewhat narrow range of augmentation techniques such as rephrasing and difficulty enhancement to boost performance. In response to this issue, we have amalgamated and further refined these strengths while broadening the scope of augmentation methods to construct a **mu**lti-perspective augmentation dataset for **math**ematics—termed **MuMath** (μ-Math) Dataset.Subsequently, we finetune LLaMA-2 on the MuMath dataset to derive the MuMath model. Our experiments indicate that our MuMath-70B model achieves new state-of-the-art performance among tool-free methods—achieving 88.3% on GSM8K and 34.5% on MATH .We release the MuMath dataset along with its corresponding models and code for public use.</abstract>
<identifier type="citekey">you-etal-2024-mumath</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.185</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2932</start>
<end>2958</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MuMath: Multi-perspective Data Augmentation for Mathematical Reasoning in Large Language Models
%A You, Weihao
%A Yin, Shuo
%A Zhao, Xudong
%A Ji, Zhilong
%A Zhong, Guoqiang
%A Bai, Jinfeng
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F you-etal-2024-mumath
%X Recently, the tool-use Large Language Models (LLMs) that integrate with external Python interpreters have significantly enhanced mathematical reasoning capabilities for open-source LLMs. However, these models fall short in demonstrating the calculation process, which compromises user-friendliness and understanding of problem-solving steps. Conversely, while tool-free methods offer a clear display of the problem-solving process, their accuracy leaves room for improvement.These tool-free methods typically employ a somewhat narrow range of augmentation techniques such as rephrasing and difficulty enhancement to boost performance. In response to this issue, we have amalgamated and further refined these strengths while broadening the scope of augmentation methods to construct a **mu**lti-perspective augmentation dataset for **math**ematics—termed **MuMath** (μ-Math) Dataset.Subsequently, we finetune LLaMA-2 on the MuMath dataset to derive the MuMath model. Our experiments indicate that our MuMath-70B model achieves new state-of-the-art performance among tool-free methods—achieving 88.3% on GSM8K and 34.5% on MATH .We release the MuMath dataset along with its corresponding models and code for public use.
%U https://aclanthology.org/2024.findings-naacl.185
%P 2932-2958
Markdown (Informal)
[MuMath: Multi-perspective Data Augmentation for Mathematical Reasoning in Large Language Models](https://aclanthology.org/2024.findings-naacl.185) (You et al., Findings 2024)
ACL