@inproceedings{moore-diana-2026-ai,
title = "{AI}-Enabled Quality Assurance for Multiple-Choice Assessment Items",
author = "Moore, Steven James and
Diana, Nicholas",
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 = "2026",
address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2026.aimecon-wip.58/",
pages = "464--471",
ISBN = "979-8-9983004-1-7",
abstract = "Generating multiple-choice questions is increasingly scalable, but establishing their quality remains difficult. We review fourteen reports on automated item-writing flaw detection, revision, psychometric screening, and benchmark auditing. High accuracy often masks weak detection of flawed items, and revision evidence is mixed. We propose evaluating quality assurance as independently validated decisions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moore-diana-2026-ai">
<titleInfo>
<title>AI-Enabled Quality Assurance for Multiple-Choice Assessment Items</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="given">James</namePart>
<namePart type="family">Moore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Diana</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): 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">979-8-9983004-1-7</identifier>
</relatedItem>
<abstract>Generating multiple-choice questions is increasingly scalable, but establishing their quality remains difficult. We review fourteen reports on automated item-writing flaw detection, revision, psychometric screening, and benchmark auditing. High accuracy often masks weak detection of flawed items, and revision evidence is mixed. We propose evaluating quality assurance as independently validated decisions.</abstract>
<identifier type="citekey">moore-diana-2026-ai</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-wip.58/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>464</start>
<end>471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI-Enabled Quality Assurance for Multiple-Choice Assessment Items
%A Moore, Steven James
%A Diana, Nicholas
%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 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-1-7
%F moore-diana-2026-ai
%X Generating multiple-choice questions is increasingly scalable, but establishing their quality remains difficult. We review fourteen reports on automated item-writing flaw detection, revision, psychometric screening, and benchmark auditing. High accuracy often masks weak detection of flawed items, and revision evidence is mixed. We propose evaluating quality assurance as independently validated decisions.
%U https://aclanthology.org/2026.aimecon-wip.58/
%P 464-471
Markdown (Informal)
[AI-Enabled Quality Assurance for Multiple-Choice Assessment Items](https://aclanthology.org/2026.aimecon-wip.58/) (Moore & Diana, AIME-Con 2026)
ACL
- Steven James Moore and Nicholas Diana. 2026. AI-Enabled Quality Assurance for Multiple-Choice Assessment Items. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 464–471, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).