<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thuy-etal-2026-simulating">
    <titleInfo>
        <title>Simulating Student Interactions for Virtual Pretesting with In-Context Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Arthur</namePart>
        <namePart type="family">Thuy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luca</namePart>
        <namePart type="family">Benedetto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ekaterina</namePart>
        <namePart type="family">Loginova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dries</namePart>
        <namePart type="given">F</namePart>
        <namePart type="family">Benoit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent research has experimented with using Large Language Models (LLMs) for simulating student responses to exam questions. This approach, known as virtual pretesting, potentially offers a scalable alternative to traditional pretesting, which is costly and time-intensive, by enabling the creation of datasets of virtual students’ responses. Prior studies focused on zero-shot role-playing, prompting one LLM to imitate students of different levels, but showed limited alignment with response patterns of real students. This work introduces a framework that improves the alignment of LLM-based student simulations through in-context learning (ICL), leveraging previous question-answer records to provide the model with richer information about students’ skills and misconceptions. Our experiments show that not all models can leverage the additional contextual information. However, a multi-model approach, which combines simulations from several models, significantly improves alignment of the simulated responses when provided with relevant context: we observe a reduction of up to 30% in difficulty estimation RMSE with respect to the non contextual and individual contextual models. Overall, our findings indicate that LLMs can be used with ICL to create synthetic datasets of student responses approximating some patterns of learner behavior, however their ability to align with authentic student performance remains limited.</abstract>
    <identifier type="citekey">thuy-etal-2026-simulating</identifier>
    <identifier type="doi">10.63317/5m57qocfb6ph</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.815/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>10376</start>
            <end>10389</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Simulating Student Interactions for Virtual Pretesting with In-Context Learning
%A Thuy, Arthur
%A Benedetto, Luca
%A Loginova, Ekaterina
%A Benoit, Dries F.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F thuy-etal-2026-simulating
%X Recent research has experimented with using Large Language Models (LLMs) for simulating student responses to exam questions. This approach, known as virtual pretesting, potentially offers a scalable alternative to traditional pretesting, which is costly and time-intensive, by enabling the creation of datasets of virtual students’ responses. Prior studies focused on zero-shot role-playing, prompting one LLM to imitate students of different levels, but showed limited alignment with response patterns of real students. This work introduces a framework that improves the alignment of LLM-based student simulations through in-context learning (ICL), leveraging previous question-answer records to provide the model with richer information about students’ skills and misconceptions. Our experiments show that not all models can leverage the additional contextual information. However, a multi-model approach, which combines simulations from several models, significantly improves alignment of the simulated responses when provided with relevant context: we observe a reduction of up to 30% in difficulty estimation RMSE with respect to the non contextual and individual contextual models. Overall, our findings indicate that LLMs can be used with ICL to create synthetic datasets of student responses approximating some patterns of learner behavior, however their ability to align with authentic student performance remains limited.
%R 10.63317/5m57qocfb6ph
%U https://aclanthology.org/2026.lrec-1.815/
%U https://doi.org/10.63317/5m57qocfb6ph
%P 10376-10389

Markdown (Informal)

[Simulating Student Interactions for Virtual Pretesting with In-Context Learning](https://aclanthology.org/2026.lrec-1.815/) (Thuy et al., LREC 2026)

• Simulating Student Interactions for Virtual Pretesting with In-Context Learning (Thuy et al., LREC 2026)

ACL

• Arthur Thuy, Luca Benedetto, Ekaterina Loginova, and Dries F. Benoit. 2026. Simulating Student Interactions for Virtual Pretesting with In-Context Learning. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 10376–10389, Palma de Mallorca, Spain. ELRA Language Resource Association.