Educators' Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chowdhury, Sankalan Pal, Zhang, Terry Jingchen, Rooein, Donya, Hovy, Dirk, Käser, Tanja, Sachan, Mrinmaya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916788145487872
author Chowdhury, Sankalan Pal
Zhang, Terry Jingchen
Rooein, Donya
Hovy, Dirk
Käser, Tanja
Sachan, Mrinmaya
author_facet Chowdhury, Sankalan Pal
Zhang, Terry Jingchen
Rooein, Donya
Hovy, Dirk
Käser, Tanja
Sachan, Mrinmaya
contents The rapid development of Large Language Models (LLMs) opens up the possibility of using them as personal 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 tutors in terms of engagement, empathy, scaffolding, and conciseness. We ask human tutors to annotate and 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08702
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Educators' Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting
Chowdhury, Sankalan Pal
Zhang, Terry Jingchen
Rooein, Donya
Hovy, Dirk
Käser, Tanja
Sachan, Mrinmaya
Emerging Technologies
The rapid development of Large Language Models (LLMs) opens up the possibility of using them as personal 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 tutors in terms of engagement, empathy, scaffolding, and conciseness. We ask human tutors to annotate and 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.
title Educators' Perceptions of Large Language Models as Tutors: Comparing Human and AI Tutors in a Blind Text-only Setting
topic Emerging Technologies
url https://arxiv.org/abs/2506.08702