@inproceedings{pal-chowdhury-etal-2025-educators,
title = "Educators' Perceptions of Large Language Models as Tutors: Comparing Human and {AI} Tutors in a Blind Text-only Setting",
author = {Pal Chowdhury, Sankalan and
Zhang, Terry Jingchen and
Rooein, Donya and
Hovy, Dirk and
K{\"a}ser, Tanja and
Sachan, Mrinmaya},
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.28/",
doi = "10.18653/v1/2025.bea-1.28",
pages = "356--374",
ISBN = "979-8-89176-270-1",
abstract = "The rapid development of Large Language Models (LLMs) opens up the possibility of using them aspersonal tutors. This has led to the development of several intelligent tutoring systems and learning assistants that use LLMs as back-ends with various degrees of engineering. In this study, we seek to compare human tutors with LLM tutorsin terms of engagement, empathy, scaffolding, and conciseness. We ask human tutors to compare the performance of an LLM tutor with that of a human tutor in teaching grade-school math word problems on these qualities. We find that annotators with teaching experience perceive LLMs as showing higher performance than human tutors in all 4 metrics. The biggest advantage is in empathy, where 80{\%} of our annotators prefer the LLM tutor more often than the human tutors. Our study paints a positive picture of LLMs as tutors and indicates that these models can be used to reduce the load on human teachers in the future."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pal-chowdhury-etal-2025-educators">
<titleInfo>
<title>Educators’ Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sankalan</namePart>
<namePart type="family">Pal Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="given">Jingchen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donya</namePart>
<namePart type="family">Rooein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Käser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mrinmaya</namePart>
<namePart type="family">Sachan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</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">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</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">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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>The rapid development of Large Language Models (LLMs) opens up the possibility of using them aspersonal tutors. This has led to the development of several intelligent tutoring systems and learning assistants that use LLMs as back-ends with various degrees of engineering. In this study, we seek to compare human tutors with LLM tutorsin terms of engagement, empathy, scaffolding, and conciseness. We ask human tutors to compare the performance of an LLM tutor with that of a human tutor in teaching grade-school math word problems on these qualities. We find that annotators with teaching experience perceive LLMs as showing higher performance than human tutors in all 4 metrics. The biggest advantage is in empathy, where 80% of our annotators prefer the LLM tutor more often than the human tutors. Our study paints a positive picture of LLMs as tutors and indicates that these models can be used to reduce the load on human teachers in the future.</abstract>
<identifier type="citekey">pal-chowdhury-etal-2025-educators</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.28</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.28/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>356</start>
<end>374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Educators’ Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting
%A Pal Chowdhury, Sankalan
%A Zhang, Terry Jingchen
%A Rooein, Donya
%A Hovy, Dirk
%A Käser, Tanja
%A Sachan, Mrinmaya
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F pal-chowdhury-etal-2025-educators
%X The rapid development of Large Language Models (LLMs) opens up the possibility of using them aspersonal tutors. This has led to the development of several intelligent tutoring systems and learning assistants that use LLMs as back-ends with various degrees of engineering. In this study, we seek to compare human tutors with LLM tutorsin terms of engagement, empathy, scaffolding, and conciseness. We ask human tutors to compare the performance of an LLM tutor with that of a human tutor in teaching grade-school math word problems on these qualities. We find that annotators with teaching experience perceive LLMs as showing higher performance than human tutors in all 4 metrics. The biggest advantage is in empathy, where 80% of our annotators prefer the LLM tutor more often than the human tutors. Our study paints a positive picture of LLMs as tutors and indicates that these models can be used to reduce the load on human teachers in the future.
%R 10.18653/v1/2025.bea-1.28
%U https://aclanthology.org/2025.bea-1.28/
%U https://doi.org/10.18653/v1/2025.bea-1.28
%P 356-374
Markdown (Informal)
[Educators’ Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting](https://aclanthology.org/2025.bea-1.28/) (Pal Chowdhury et al., BEA 2025)
ACL