@inproceedings{demirkaya-johnson-2026-simulating,
title = "Simulating Examinee Responses to Figure Matrices Items Using {VLM}s for Item Evaluation",
author = "Demirkaya, Onur and
Johnson, Evelyn",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting-Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Full Papers",
month = oct,
year = "2026",
address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2026.aimecon-main.56/",
pages = "497--505",
ISBN = "979-8-9983004-0-0",
abstract = "This study evaluated whether visual embeddings from SigLIP and DINOv2 could be used to simulate responses to Figure Matrices items. Models predicted response probabilities using item screenshots and examinee ability estimates. Results showed moderate probability recovery but limited item difficulty recovery, indicating promise for early screening but not calibration replacement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demirkaya-johnson-2026-simulating">
<titleInfo>
<title>Simulating Examinee Responses to Figure Matrices Items Using VLMs for Item Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Onur</namePart>
<namePart type="family">Demirkaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evelyn</namePart>
<namePart type="family">Johnson</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 Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers</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">979-8-9983004-0-0</identifier>
</relatedItem>
<abstract>This study evaluated whether visual embeddings from SigLIP and DINOv2 could be used to simulate responses to Figure Matrices items. Models predicted response probabilities using item screenshots and examinee ability estimates. Results showed moderate probability recovery but limited item difficulty recovery, indicating promise for early screening but not calibration replacement.</abstract>
<identifier type="citekey">demirkaya-johnson-2026-simulating</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-main.56/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>497</start>
<end>505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simulating Examinee Responses to Figure Matrices Items Using VLMs for Item Evaluation
%A Demirkaya, Onur
%A Johnson, Evelyn
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-0-0
%F demirkaya-johnson-2026-simulating
%X This study evaluated whether visual embeddings from SigLIP and DINOv2 could be used to simulate responses to Figure Matrices items. Models predicted response probabilities using item screenshots and examinee ability estimates. Results showed moderate probability recovery but limited item difficulty recovery, indicating promise for early screening but not calibration replacement.
%U https://aclanthology.org/2026.aimecon-main.56/
%P 497-505
Markdown (Informal)
[Simulating Examinee Responses to Figure Matrices Items Using VLMs for Item Evaluation](https://aclanthology.org/2026.aimecon-main.56/) (Demirkaya & Johnson, AIME-Con 2026)
ACL