@inproceedings{furuhashi-etal-2026-well,
title = "How Well Can {LLM}s Simulate Real Learner Evaluations of Educational Feedback?",
author = "Furuhashi, Momoka and
Nakayama, Kouta and
Kodama, Takashi and
Sugawara, Saku and
Takami, Kyosuke",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1378/",
pages = "31473--31493",
ISBN = "979-8-89176-459-0",
abstract = "While recent studies have explored human behavior and preference simulation using large language models (LLMs), it remains unclear how well LLMs can simulate subjective evaluations from real learners in educational settings. We investigate this question using real learner evaluation data on feedback for high-school biology questions at both the group and individual levels. We compare performance with and without learner-specific information, such as personality traits and evaluation examples, across six models. Our results show that LLMs still have a limited ability to simulate learner evaluations. Providing learner profiles and examples improves score calibration and individual-level simulation, but more often fails to improve group-level consistency. These findings highlight the need to investigate which learner information and adaptation strategies are effective for learner preference simulation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="furuhashi-etal-2026-well">
<titleInfo>
<title>How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Momoka</namePart>
<namePart type="family">Furuhashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kouta</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Kodama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saku</namePart>
<namePart type="family">Sugawara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Takami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>While recent studies have explored human behavior and preference simulation using large language models (LLMs), it remains unclear how well LLMs can simulate subjective evaluations from real learners in educational settings. We investigate this question using real learner evaluation data on feedback for high-school biology questions at both the group and individual levels. We compare performance with and without learner-specific information, such as personality traits and evaluation examples, across six models. Our results show that LLMs still have a limited ability to simulate learner evaluations. Providing learner profiles and examples improves score calibration and individual-level simulation, but more often fails to improve group-level consistency. These findings highlight the need to investigate which learner information and adaptation strategies are effective for learner preference simulation.</abstract>
<identifier type="citekey">furuhashi-etal-2026-well</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1378/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31473</start>
<end>31493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?
%A Furuhashi, Momoka
%A Nakayama, Kouta
%A Kodama, Takashi
%A Sugawara, Saku
%A Takami, Kyosuke
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F furuhashi-etal-2026-well
%X While recent studies have explored human behavior and preference simulation using large language models (LLMs), it remains unclear how well LLMs can simulate subjective evaluations from real learners in educational settings. We investigate this question using real learner evaluation data on feedback for high-school biology questions at both the group and individual levels. We compare performance with and without learner-specific information, such as personality traits and evaluation examples, across six models. Our results show that LLMs still have a limited ability to simulate learner evaluations. Providing learner profiles and examples improves score calibration and individual-level simulation, but more often fails to improve group-level consistency. These findings highlight the need to investigate which learner information and adaptation strategies are effective for learner preference simulation.
%U https://aclanthology.org/2026.emnlp-main.1378/
%P 31473-31493
Markdown (Informal)
[How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?](https://aclanthology.org/2026.emnlp-main.1378/) (Furuhashi et al., EMNLP 2026)
ACL