@inproceedings{upadhyay-etal-2023-improving,
title = "Improving Mathematics Tutoring With A Code Scratchpad",
author = "Upadhyay, Shriyash and
Ginsberg, Etan and
Callison-Burch, Chris",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.2",
doi = "10.18653/v1/2023.bea-1.2",
pages = "20--28",
abstract = "Large language models can solve reasoning tasks (like math problems) more effectively when they are allowed to generate rationales. However, a good tutoring system should not just generate solutions, but should also generate explanations and should be able to correct and guide students. We show that providing a code scratchpad improves performance on each tutoring step with a gradeschool mathematics dataset. On these tutoring tasks, GPT-3 models provided with a code scratchpad significantly outperform those given only a language scratchpad (77.7{\%} vs 48.7{\%} cumulative accuracy).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="upadhyay-etal-2023-improving">
<titleInfo>
<title>Improving Mathematics Tutoring With A Code Scratchpad</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shriyash</namePart>
<namePart type="family">Upadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Etan</namePart>
<namePart type="family">Ginsberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models can solve reasoning tasks (like math problems) more effectively when they are allowed to generate rationales. However, a good tutoring system should not just generate solutions, but should also generate explanations and should be able to correct and guide students. We show that providing a code scratchpad improves performance on each tutoring step with a gradeschool mathematics dataset. On these tutoring tasks, GPT-3 models provided with a code scratchpad significantly outperform those given only a language scratchpad (77.7% vs 48.7% cumulative accuracy).</abstract>
<identifier type="citekey">upadhyay-etal-2023-improving</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.2</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>20</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Mathematics Tutoring With A Code Scratchpad
%A Upadhyay, Shriyash
%A Ginsberg, Etan
%A Callison-Burch, Chris
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F upadhyay-etal-2023-improving
%X Large language models can solve reasoning tasks (like math problems) more effectively when they are allowed to generate rationales. However, a good tutoring system should not just generate solutions, but should also generate explanations and should be able to correct and guide students. We show that providing a code scratchpad improves performance on each tutoring step with a gradeschool mathematics dataset. On these tutoring tasks, GPT-3 models provided with a code scratchpad significantly outperform those given only a language scratchpad (77.7% vs 48.7% cumulative accuracy).
%R 10.18653/v1/2023.bea-1.2
%U https://aclanthology.org/2023.bea-1.2
%U https://doi.org/10.18653/v1/2023.bea-1.2
%P 20-28
Markdown (Informal)
[Improving Mathematics Tutoring With A Code Scratchpad](https://aclanthology.org/2023.bea-1.2) (Upadhyay et al., BEA 2023)
ACL
- Shriyash Upadhyay, Etan Ginsberg, and Chris Callison-Burch. 2023. Improving Mathematics Tutoring With A Code Scratchpad. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 20–28, Toronto, Canada. Association for Computational Linguistics.