@inproceedings{niousha-etal-2026-parastudent,
title = "{P}ara{S}tudent: Closing the {S}im2{R}eal Gap in User Simulators for {AI} Tutor Evaluation",
author = "Niousha, Rose and
Miroyan, Mihran and
O{'}Neill, Abigail and
Gonzalez, Joseph E. and
Ranade, Gireeja and
DeNero, John and
Norouzi, Narges",
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.2488/",
pages = "56493--56511",
ISBN = "979-8-89176-459-0",
abstract = "Evaluating Artificial Intelligence (AI) tutor feedback before deployment requires anticipating student engagement, typically assessed through real interaction data. We introduce ParaStudent, a fine-tuning framework for simulating novice programming revisions to support AI tutor evaluation. Compared with prompted baselines, ParaStudent{'}s revisions more closely match real student code distributions across functional, stylistic, and semantic metrics. Our best variant achieves AUCs of 0.80 for both feedback relevance and successful uptake when distinguishing streams with real engagement above versus at or below the median, while prompted baselines remain near chance on successful uptake. These findings demonstrate the promise of simulated engagement for pre-deployment feedback triage."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niousha-etal-2026-parastudent">
<titleInfo>
<title>ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rose</namePart>
<namePart type="family">Niousha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihran</namePart>
<namePart type="family">Miroyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abigail</namePart>
<namePart type="family">O’Neill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Gonzalez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gireeja</namePart>
<namePart type="family">Ranade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">DeNero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Narges</namePart>
<namePart type="family">Norouzi</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>Evaluating Artificial Intelligence (AI) tutor feedback before deployment requires anticipating student engagement, typically assessed through real interaction data. We introduce ParaStudent, a fine-tuning framework for simulating novice programming revisions to support AI tutor evaluation. Compared with prompted baselines, ParaStudent’s revisions more closely match real student code distributions across functional, stylistic, and semantic metrics. Our best variant achieves AUCs of 0.80 for both feedback relevance and successful uptake when distinguishing streams with real engagement above versus at or below the median, while prompted baselines remain near chance on successful uptake. These findings demonstrate the promise of simulated engagement for pre-deployment feedback triage.</abstract>
<identifier type="citekey">niousha-etal-2026-parastudent</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2488/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>56493</start>
<end>56511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation
%A Niousha, Rose
%A Miroyan, Mihran
%A O’Neill, Abigail
%A Gonzalez, Joseph E.
%A Ranade, Gireeja
%A DeNero, John
%A Norouzi, Narges
%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 niousha-etal-2026-parastudent
%X Evaluating Artificial Intelligence (AI) tutor feedback before deployment requires anticipating student engagement, typically assessed through real interaction data. We introduce ParaStudent, a fine-tuning framework for simulating novice programming revisions to support AI tutor evaluation. Compared with prompted baselines, ParaStudent’s revisions more closely match real student code distributions across functional, stylistic, and semantic metrics. Our best variant achieves AUCs of 0.80 for both feedback relevance and successful uptake when distinguishing streams with real engagement above versus at or below the median, while prompted baselines remain near chance on successful uptake. These findings demonstrate the promise of simulated engagement for pre-deployment feedback triage.
%U https://aclanthology.org/2026.emnlp-main.2488/
%P 56493-56511
Markdown (Informal)
[ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation](https://aclanthology.org/2026.emnlp-main.2488/) (Niousha et al., EMNLP 2026)
ACL