@inproceedings{kim-etal-2026-validity,
title = "A Validity Argument Framework for Automated Item Generation Systems",
author = "Kim, Euigyum and
Shin, Hyo Jeong and
von Davier, Alina",
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.57/",
pages = "506--515",
ISBN = "979-8-9983004-0-0",
abstract = "We introduce an evidence-centered, argument-based framework for validating AI-generated assessment items. The framework organizes three claims{---}content comparability, construct validity, and psychometric functioning{---}with assumptions and evidence. Applying the framework to critical thinking assessments, we compared AI-generated and human-authored items and identified distinct mechanisms underlying the validity of AI-generated items."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-validity">
<titleInfo>
<title>A Validity Argument Framework for Automated Item Generation Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Euigyum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyo</namePart>
<namePart type="given">Jeong</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">von Davier</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>We introduce an evidence-centered, argument-based framework for validating AI-generated assessment items. The framework organizes three claims—content comparability, construct validity, and psychometric functioning—with assumptions and evidence. Applying the framework to critical thinking assessments, we compared AI-generated and human-authored items and identified distinct mechanisms underlying the validity of AI-generated items.</abstract>
<identifier type="citekey">kim-etal-2026-validity</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-main.57/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>506</start>
<end>515</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Validity Argument Framework for Automated Item Generation Systems
%A Kim, Euigyum
%A Shin, Hyo Jeong
%A von Davier, Alina
%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 kim-etal-2026-validity
%X We introduce an evidence-centered, argument-based framework for validating AI-generated assessment items. The framework organizes three claims—content comparability, construct validity, and psychometric functioning—with assumptions and evidence. Applying the framework to critical thinking assessments, we compared AI-generated and human-authored items and identified distinct mechanisms underlying the validity of AI-generated items.
%U https://aclanthology.org/2026.aimecon-main.57/
%P 506-515
Markdown (Informal)
[A Validity Argument Framework for Automated Item Generation Systems](https://aclanthology.org/2026.aimecon-main.57/) (Kim et al., AIME-Con 2026)
ACL
- Euigyum Kim, Hyo Jeong Shin, and Alina von Davier. 2026. A Validity Argument Framework for Automated Item Generation Systems. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 506–515, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).