@inproceedings{van-ness-etal-2026-evaluating,
title = "Evaluating an {AI}-Item Generation Tool for {NAEP} Mathematics",
author = "Van Ness, Cheryl and
Minchuk, Ilona and
Parker, Karen",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting-Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Coordinated Session 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-sessions.20/",
pages = "196--202",
ISBN = "979-8-9983004-2-4",
abstract = "This study evaluates the effectiveness of an AI-based system (Wilbur) for generating NAEP mathematics items. Results from this investigation indicate moderate success for content-focused items but substantial challenges for items intended to assess the NAEP Mathematical Practices. Transitioning from GPT-4 to GPT-5.2 improved item quality, though human revision remained essential."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-ness-etal-2026-evaluating">
<titleInfo>
<title>Evaluating an AI-Item Generation Tool for NAEP Mathematics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheryl</namePart>
<namePart type="family">Van Ness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilona</namePart>
<namePart type="family">Minchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Parker</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): Coordinated Session 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">979-8-9983004-2-4</identifier>
</relatedItem>
<abstract>This study evaluates the effectiveness of an AI-based system (Wilbur) for generating NAEP mathematics items. Results from this investigation indicate moderate success for content-focused items but substantial challenges for items intended to assess the NAEP Mathematical Practices. Transitioning from GPT-4 to GPT-5.2 improved item quality, though human revision remained essential.</abstract>
<identifier type="citekey">van-ness-etal-2026-evaluating</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-sessions.20/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>196</start>
<end>202</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating an AI-Item Generation Tool for NAEP Mathematics
%A Van Ness, Cheryl
%A Minchuk, Ilona
%A Parker, Karen
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-2-4
%F van-ness-etal-2026-evaluating
%X This study evaluates the effectiveness of an AI-based system (Wilbur) for generating NAEP mathematics items. Results from this investigation indicate moderate success for content-focused items but substantial challenges for items intended to assess the NAEP Mathematical Practices. Transitioning from GPT-4 to GPT-5.2 improved item quality, though human revision remained essential.
%U https://aclanthology.org/2026.aimecon-sessions.20/
%P 196-202
Markdown (Informal)
[Evaluating an AI-Item Generation Tool for NAEP Mathematics](https://aclanthology.org/2026.aimecon-sessions.20/) (Van Ness et al., AIME-Con 2026)
ACL
- Cheryl Van Ness, Ilona Minchuk, and Karen Parker. 2026. Evaluating an AI-Item Generation Tool for NAEP Mathematics. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 196–202, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).