@inproceedings{meador-2026-expert,
title = "From Expert Approval to Validity Evidence: Evaluating {AI}-Generated Assessment Items",
author = "Meador, Chris",
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.18/",
pages = "180--188",
ISBN = "979-8-9983004-2-4",
abstract = "Expert approval certifies that test developers would use AI-generated items, not that the scores support valid interpretations. I extend argument-based validity with a generation inference and a five-layer evidence framework, apply it diagnostically to three NAEP{--}Wilbur evaluations, and propose design principles and a minimal reporting standard for the field."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meador-2026-expert">
<titleInfo>
<title>From Expert Approval to Validity Evidence: Evaluating AI-Generated Assessment Items</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Meador</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>Expert approval certifies that test developers would use AI-generated items, not that the scores support valid interpretations. I extend argument-based validity with a generation inference and a five-layer evidence framework, apply it diagnostically to three NAEP–Wilbur evaluations, and propose design principles and a minimal reporting standard for the field.</abstract>
<identifier type="citekey">meador-2026-expert</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-sessions.18/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>180</start>
<end>188</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Expert Approval to Validity Evidence: Evaluating AI-Generated Assessment Items
%A Meador, Chris
%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 meador-2026-expert
%X Expert approval certifies that test developers would use AI-generated items, not that the scores support valid interpretations. I extend argument-based validity with a generation inference and a five-layer evidence framework, apply it diagnostically to three NAEP–Wilbur evaluations, and propose design principles and a minimal reporting standard for the field.
%U https://aclanthology.org/2026.aimecon-sessions.18/
%P 180-188
Markdown (Informal)
[From Expert Approval to Validity Evidence: Evaluating AI-Generated Assessment Items](https://aclanthology.org/2026.aimecon-sessions.18/) (Meador, AIME-Con 2026)
ACL