@inproceedings{chen-etal-2026-responsible,
title = "Responsible {AI} in the {D}uolingo {E}nglish Test: Case Studies with Automatic Item Creation and Session-Level Quality Monitoring",
author = "Chen, Siyuan Marco and
Zhang, Xiaowan and
Runge, Andrew and
Church, Jacqueline",
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.12/",
pages = "101--109",
ISBN = "979-8-9983004-2-4",
abstract = "Digital-first assessments are delivered continuously and often remotely. Artificial intelligence (AI) enables digital assessments to generate content and administer tests at scale. Like any system used for high-stakes decision-making, digital assessments require responsible AI (RAI) practices to ensure fairness and validity. This paper presents two deployed systems in the Duolingo English Test (DET) lifecycle that align the DET to its RAI Standards. The Item Factory combines automated item generation with staged expert review; the Analytics for Quality Assurance in Test Taker (AQUA-TT) system applies unsupervised anomaly detection methods to continuously monitor for issues in digital test deliveries for daily individual test sessions. We present the design and performance of these systems and discuss what they imply for placing human judgment inside digital assessments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-responsible">
<titleInfo>
<title>Responsible AI in the Duolingo English Test: Case Studies with Automatic Item Creation and Session-Level Quality Monitoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyuan</namePart>
<namePart type="given">Marco</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaowan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Runge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacqueline</namePart>
<namePart type="family">Church</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>Digital-first assessments are delivered continuously and often remotely. Artificial intelligence (AI) enables digital assessments to generate content and administer tests at scale. Like any system used for high-stakes decision-making, digital assessments require responsible AI (RAI) practices to ensure fairness and validity. This paper presents two deployed systems in the Duolingo English Test (DET) lifecycle that align the DET to its RAI Standards. The Item Factory combines automated item generation with staged expert review; the Analytics for Quality Assurance in Test Taker (AQUA-TT) system applies unsupervised anomaly detection methods to continuously monitor for issues in digital test deliveries for daily individual test sessions. We present the design and performance of these systems and discuss what they imply for placing human judgment inside digital assessments.</abstract>
<identifier type="citekey">chen-etal-2026-responsible</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-sessions.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>101</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Responsible AI in the Duolingo English Test: Case Studies with Automatic Item Creation and Session-Level Quality Monitoring
%A Chen, Siyuan Marco
%A Zhang, Xiaowan
%A Runge, Andrew
%A Church, Jacqueline
%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 chen-etal-2026-responsible
%X Digital-first assessments are delivered continuously and often remotely. Artificial intelligence (AI) enables digital assessments to generate content and administer tests at scale. Like any system used for high-stakes decision-making, digital assessments require responsible AI (RAI) practices to ensure fairness and validity. This paper presents two deployed systems in the Duolingo English Test (DET) lifecycle that align the DET to its RAI Standards. The Item Factory combines automated item generation with staged expert review; the Analytics for Quality Assurance in Test Taker (AQUA-TT) system applies unsupervised anomaly detection methods to continuously monitor for issues in digital test deliveries for daily individual test sessions. We present the design and performance of these systems and discuss what they imply for placing human judgment inside digital assessments.
%U https://aclanthology.org/2026.aimecon-sessions.12/
%P 101-109
Markdown (Informal)
[Responsible AI in the Duolingo English Test: Case Studies with Automatic Item Creation and Session-Level Quality Monitoring](https://aclanthology.org/2026.aimecon-sessions.12/) (Chen et al., AIME-Con 2026)
ACL