@inproceedings{xu-etal-2025-large,
title = "Can Large Language Models Be Good Language Teachers?",
author = "Xu, LiQing and
Li, Qiwei and
Peng, Tianshuo and
Li, Zuchao and
Zhao, Hai and
Wang, Ping",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1222/",
pages = "23968--23982",
ISBN = "979-8-89176-332-6",
abstract = "Large language models (LLMs) have achieved remarkable success across diverse domains. However, their potential as effective language teachers{---}particularly in complex pedagogical scenarios like teaching Chinese as a second language{---}remains inadequately assessed. To address this gap, we propose the first pedagogical competence benchmark for LLMs, rigorously evaluating their performance against international standards for Chinese language teachers. Our framework spans three core dimensions: (1) basic knowledge evaluation, covering 32 subtopics across five major categories; (2) international teacher examination, based on data collected from international Chinese teacher certification exams; and (3) teaching practice evaluation, where target LLMs summarize knowledge points and design instructional content for student models, followed by testing the student models to assess the LLM{'}s ability to distill and teach key concepts.We conduct a comprehensive evaluation of 13 latest multilingual and Chinese LLMs. While most models demonstrate promising pedagogical potential, there remains substantial room for improvement in their teaching capabilities. This study contributes to the development of AI-assisted language education tools capable of rivaling human teaching excellence. The benchmark dataset and evaluation scripts used in this study are publicly available at https://github.com/Line-Kite/CLTE."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2025-large">
<titleInfo>
<title>Can Large Language Models Be Good Language Teachers?</title>
</titleInfo>
<name type="personal">
<namePart type="given">LiQing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiwei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianshuo</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zuchao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have achieved remarkable success across diverse domains. However, their potential as effective language teachers—particularly in complex pedagogical scenarios like teaching Chinese as a second language—remains inadequately assessed. To address this gap, we propose the first pedagogical competence benchmark for LLMs, rigorously evaluating their performance against international standards for Chinese language teachers. Our framework spans three core dimensions: (1) basic knowledge evaluation, covering 32 subtopics across five major categories; (2) international teacher examination, based on data collected from international Chinese teacher certification exams; and (3) teaching practice evaluation, where target LLMs summarize knowledge points and design instructional content for student models, followed by testing the student models to assess the LLM’s ability to distill and teach key concepts.We conduct a comprehensive evaluation of 13 latest multilingual and Chinese LLMs. While most models demonstrate promising pedagogical potential, there remains substantial room for improvement in their teaching capabilities. This study contributes to the development of AI-assisted language education tools capable of rivaling human teaching excellence. The benchmark dataset and evaluation scripts used in this study are publicly available at https://github.com/Line-Kite/CLTE.</abstract>
<identifier type="citekey">xu-etal-2025-large</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1222/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>23968</start>
<end>23982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Large Language Models Be Good Language Teachers?
%A Xu, LiQing
%A Li, Qiwei
%A Peng, Tianshuo
%A Li, Zuchao
%A Zhao, Hai
%A Wang, Ping
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F xu-etal-2025-large
%X Large language models (LLMs) have achieved remarkable success across diverse domains. However, their potential as effective language teachers—particularly in complex pedagogical scenarios like teaching Chinese as a second language—remains inadequately assessed. To address this gap, we propose the first pedagogical competence benchmark for LLMs, rigorously evaluating their performance against international standards for Chinese language teachers. Our framework spans three core dimensions: (1) basic knowledge evaluation, covering 32 subtopics across five major categories; (2) international teacher examination, based on data collected from international Chinese teacher certification exams; and (3) teaching practice evaluation, where target LLMs summarize knowledge points and design instructional content for student models, followed by testing the student models to assess the LLM’s ability to distill and teach key concepts.We conduct a comprehensive evaluation of 13 latest multilingual and Chinese LLMs. While most models demonstrate promising pedagogical potential, there remains substantial room for improvement in their teaching capabilities. This study contributes to the development of AI-assisted language education tools capable of rivaling human teaching excellence. The benchmark dataset and evaluation scripts used in this study are publicly available at https://github.com/Line-Kite/CLTE.
%U https://aclanthology.org/2025.emnlp-main.1222/
%P 23968-23982
Markdown (Informal)
[Can Large Language Models Be Good Language Teachers?](https://aclanthology.org/2025.emnlp-main.1222/) (Xu et al., EMNLP 2025)
ACL
- LiQing Xu, Qiwei Li, Tianshuo Peng, Zuchao Li, Hai Zhao, and Ping Wang. 2025. Can Large Language Models Be Good Language Teachers?. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 23968–23982, Suzhou, China. Association for Computational Linguistics.