@inproceedings{guo-etal-2024-exploring,
title = "Exploring Reversal Mathematical Reasoning Ability for Large Language Models",
author = "Guo, Pei and
You, WangJie and
Li, Juntao and
Bowen, Yan and
Zhang, Min",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.811",
pages = "13671--13685",
abstract = "Large language models (LLMs) have presented remarkable capabilities in the wide range of natural language understanding and reasoning tasks. Despite their success, a few works indicate that LLMs suffer from the {``}reversal curse{''}, in which LLMs can{'}t employ the inverted structure {``}B is A{''} when they are trained based on {``}A is B{''}. To explore the effect of the {``}reversal curse{''} for LLMs on complex mathematical reasoning tasks, we present two reversal datasets upon GSM8K and MathQA and verify that LLMs also struggle to solve reversal mathematical problems. We analyze the potential reason and attribute it to the insufficient modeling of the relationship between reasoning steps caused by the left-to-right objective. Consequently, based on the characteristics of multi-step reasoning, we design a novel training method to improve the general and reversal reasoning abilities. Finally, we conduct experiments on four mathematical datasets, and the results demonstrate that our method significantly improves the general reasoning capacities and alleviates the reversal problem. Our datasets and codes are available at https: //github.com/AllForward/ReversalMath.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-exploring">
<titleInfo>
<title>Exploring Reversal Mathematical Reasoning Ability for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">WangJie</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Bowen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) have presented remarkable capabilities in the wide range of natural language understanding and reasoning tasks. Despite their success, a few works indicate that LLMs suffer from the “reversal curse”, in which LLMs can’t employ the inverted structure “B is A” when they are trained based on “A is B”. To explore the effect of the “reversal curse” for LLMs on complex mathematical reasoning tasks, we present two reversal datasets upon GSM8K and MathQA and verify that LLMs also struggle to solve reversal mathematical problems. We analyze the potential reason and attribute it to the insufficient modeling of the relationship between reasoning steps caused by the left-to-right objective. Consequently, based on the characteristics of multi-step reasoning, we design a novel training method to improve the general and reversal reasoning abilities. Finally, we conduct experiments on four mathematical datasets, and the results demonstrate that our method significantly improves the general reasoning capacities and alleviates the reversal problem. Our datasets and codes are available at https: //github.com/AllForward/ReversalMath.</abstract>
<identifier type="citekey">guo-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.811</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13671</start>
<end>13685</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Reversal Mathematical Reasoning Ability for Large Language Models
%A Guo, Pei
%A You, WangJie
%A Li, Juntao
%A Bowen, Yan
%A Zhang, Min
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F guo-etal-2024-exploring
%X Large language models (LLMs) have presented remarkable capabilities in the wide range of natural language understanding and reasoning tasks. Despite their success, a few works indicate that LLMs suffer from the “reversal curse”, in which LLMs can’t employ the inverted structure “B is A” when they are trained based on “A is B”. To explore the effect of the “reversal curse” for LLMs on complex mathematical reasoning tasks, we present two reversal datasets upon GSM8K and MathQA and verify that LLMs also struggle to solve reversal mathematical problems. We analyze the potential reason and attribute it to the insufficient modeling of the relationship between reasoning steps caused by the left-to-right objective. Consequently, based on the characteristics of multi-step reasoning, we design a novel training method to improve the general and reversal reasoning abilities. Finally, we conduct experiments on four mathematical datasets, and the results demonstrate that our method significantly improves the general reasoning capacities and alleviates the reversal problem. Our datasets and codes are available at https: //github.com/AllForward/ReversalMath.
%U https://aclanthology.org/2024.findings-acl.811
%P 13671-13685
Markdown (Informal)
[Exploring Reversal Mathematical Reasoning Ability for Large Language Models](https://aclanthology.org/2024.findings-acl.811) (Guo et al., Findings 2024)
ACL