@inproceedings{johnson-etal-2025-predicting,
title = "Predicting and Evaluating Item Responses Using Machine Learning, Text Embeddings, and {LLM}s",
author = "Johnson, Evelyn and
Wei, Hsin-Ro and
Wu, Tong and
Liu, Huan",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress",
month = oct,
year = "2025",
address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2025.aimecon-wip.8/",
pages = "66--70",
ISBN = "979-8-218-84229-1",
abstract = "This work-in-progress study compares the accuracy of machine learning and large language models to predict student responses to field-test items on a social-emotional learning assessment. We evaluate how well each method replicates actual responses and examine the item parameters generated by synthetic data to those derived from actual student data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johnson-etal-2025-predicting">
<titleInfo>
<title>Predicting and Evaluating Item Responses Using Machine Learning, Text Embeddings, and LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evelyn</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Ro</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ormerod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalen</namePart>
<namePart type="family">Beiting Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>National Council on Measurement in Education (NCME)</publisher>
<place>
<placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-218-84229-1</identifier>
</relatedItem>
<abstract>This work-in-progress study compares the accuracy of machine learning and large language models to predict student responses to field-test items on a social-emotional learning assessment. We evaluate how well each method replicates actual responses and examine the item parameters generated by synthetic data to those derived from actual student data.</abstract>
<identifier type="citekey">johnson-etal-2025-predicting</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-wip.8/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>66</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting and Evaluating Item Responses Using Machine Learning, Text Embeddings, and LLMs
%A Johnson, Evelyn
%A Wei, Hsin-Ro
%A Wu, Tong
%A Liu, Huan
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84229-1
%F johnson-etal-2025-predicting
%X This work-in-progress study compares the accuracy of machine learning and large language models to predict student responses to field-test items on a social-emotional learning assessment. We evaluate how well each method replicates actual responses and examine the item parameters generated by synthetic data to those derived from actual student data.
%U https://aclanthology.org/2025.aimecon-wip.8/
%P 66-70
Markdown (Informal)
[Predicting and Evaluating Item Responses Using Machine Learning, Text Embeddings, and LLMs](https://aclanthology.org/2025.aimecon-wip.8/) (Johnson et al., AIME-Con 2025)
ACL
- Evelyn Johnson, Hsin-Ro Wei, Tong Wu, and Huan Liu. 2025. Predicting and Evaluating Item Responses Using Machine Learning, Text Embeddings, and LLMs. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 66–70, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).