Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

An Zi Yen; Wei Ling Hsu

doi:10.18653/v1/2023.findings-emnlp.201

Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

An Zi Yen^*, Wei Ling Hsu

^*此作品的通信作者

研究成果: Conference contribution › 同行評審

3 引文斯高帕斯（Scopus）

摘要

Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.

原文	English
主出版物標題	Findings of the Association for Computational Linguistics
主出版物子標題	EMNLP 2023
發行者	Association for Computational Linguistics (ACL)
頁面	3055-3069
頁數	15
ISBN（電子）	9798891760615
DOIs	https://doi.org/10.18653/v1/2023.findings-emnlp.201
出版狀態	Published - 2023
事件	2023 Findings of the Association for Computational Linguistics: EMNLP 2023 - Singapore, 新加坡持續時間: 6 12月 2023 → 10 12月 2023

出版系列

名字	Findings of the Association for Computational Linguistics: EMNLP 2023

Conference

Conference	2023 Findings of the Association for Computational Linguistics: EMNLP 2023
國家/地區	新加坡
城市	Singapore
期間	6/12/23 → 10/12/23

存取文件

10.18653/v1/2023.findings-emnlp.201

其它文件與鏈接

Link to publication in Scopus

引用此

Yen, A. Z., & Hsu, W. L. (2023). Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning. 於 Findings of the Association for Computational Linguistics: EMNLP 2023 (頁 3055-3069). (Findings of the Association for Computational Linguistics: EMNLP 2023). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.findings-emnlp.201

@inproceedings{2968041343d64f34811da7e1024c205a,

title = "Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning",

abstract = "Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.",

author = "Yen, {An Zi} and Hsu, {Wei Ling}",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 2023 Findings of the Association for Computational Linguistics: EMNLP 2023 ; Conference date: 06-12-2023 Through 10-12-2023",

year = "2023",

doi = "10.18653/v1/2023.findings-emnlp.201",

language = "English",

series = "Findings of the Association for Computational Linguistics: EMNLP 2023",

publisher = "Association for Computational Linguistics (ACL)",

pages = "3055--3069",

booktitle = "Findings of the Association for Computational Linguistics",

address = "美國",

}

Yen, AZ & Hsu, WL 2023, Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning. 於 Findings of the Association for Computational Linguistics: EMNLP 2023. Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics (ACL), 頁 3055-3069, 2023 Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, 新加坡, 6/12/23. https://doi.org/10.18653/v1/2023.findings-emnlp.201

Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning. / Yen, An Zi; Hsu, Wei Ling.
Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics (ACL), 2023. p. 3055-3069 (Findings of the Association for Computational Linguistics: EMNLP 2023).

研究成果: Conference contribution › 同行評審

TY - GEN

T1 - Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

AU - Yen, An Zi

AU - Hsu, Wei Ling

PY - 2023

Y1 - 2023

N2 - Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.

AB - Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of LLMs in helping students to learn mathematics. In this position paper, we discuss the challenges associated with employing LLMs to enhance students' mathematical problem-solving skills by providing adaptive feedback. Apart from generating the wrong reasoning processes, LLMs can misinterpret the meaning of the question, and also exhibit difficulty in understanding the given questions' rationales when attempting to correct students' answers. Three research questions are formulated.

UR - http://www.scopus.com/inward/record.url?scp=85183311861&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.findings-emnlp.201

DO - 10.18653/v1/2023.findings-emnlp.201

M3 - Conference contribution

AN - SCOPUS:85183311861

T3 - Findings of the Association for Computational Linguistics: EMNLP 2023

SP - 3055

EP - 3069

BT - Findings of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

T2 - 2023 Findings of the Association for Computational Linguistics: EMNLP 2023

Y2 - 6 December 2023 through 10 December 2023

ER -

Three Questions Concerning the Use of Large Language Models to Facilitate Mathematics Learning

摘要

出版系列

Conference

存取文件

其它文件與鏈接

指紋

引用此