@inproceedings{afrin-etal-2025-toward,
title = "Toward Automated Evaluation of {AI}-Generated Item Drafts in Clinical Assessment",
author = "Afrin, Tazin and
Ha, Le An and
Yaneva, Victoria and
Evanini, Keelan and
Go, Steven and
DeRuchie, Kristine and
Heilig, Michael",
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 = "2025",
address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2025.aimecon-main.19/",
pages = "172--182",
ISBN = "979-8-218-84228-4",
abstract = "This study examines the classification of AI-generated clinical multiple-choice questions drafts as ``helpful'' or ``non-helpful'' starting points. Expert judgments were analyzed, and multiple classifiers were evaluated{---}including feature-based models, fine-tuned transformers, and few-shot prompting with GPT-4. Our findings highlight the challenges and considerations for evaluation methods of AI-generated items in clinical test development."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afrin-etal-2025-toward">
<titleInfo>
<title>Toward Automated Evaluation of AI-Generated Item Drafts in Clinical Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tazin</namePart>
<namePart type="family">Afrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="given">An</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keelan</namePart>
<namePart type="family">Evanini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Go</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristine</namePart>
<namePart type="family">DeRuchie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Heilig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</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">979-8-218-84228-4</identifier>
</relatedItem>
<abstract>This study examines the classification of AI-generated clinical multiple-choice questions drafts as “helpful” or “non-helpful” starting points. Expert judgments were analyzed, and multiple classifiers were evaluated—including feature-based models, fine-tuned transformers, and few-shot prompting with GPT-4. Our findings highlight the challenges and considerations for evaluation methods of AI-generated items in clinical test development.</abstract>
<identifier type="citekey">afrin-etal-2025-toward</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-main.19/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>172</start>
<end>182</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toward Automated Evaluation of AI-Generated Item Drafts in Clinical Assessment
%A Afrin, Tazin
%A Ha, Le An
%A Yaneva, Victoria
%A Evanini, Keelan
%A Go, Steven
%A DeRuchie, Kristine
%A Heilig, Michael
%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 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84228-4
%F afrin-etal-2025-toward
%X This study examines the classification of AI-generated clinical multiple-choice questions drafts as “helpful” or “non-helpful” starting points. Expert judgments were analyzed, and multiple classifiers were evaluated—including feature-based models, fine-tuned transformers, and few-shot prompting with GPT-4. Our findings highlight the challenges and considerations for evaluation methods of AI-generated items in clinical test development.
%U https://aclanthology.org/2025.aimecon-main.19/
%P 172-182
Markdown (Informal)
[Toward Automated Evaluation of AI-Generated Item Drafts in Clinical Assessment](https://aclanthology.org/2025.aimecon-main.19/) (Afrin et al., AIME-Con 2025)
ACL
- Tazin Afrin, Le An Ha, Victoria Yaneva, Keelan Evanini, Steven Go, Kristine DeRuchie, and Michael Heilig. 2025. Toward Automated Evaluation of AI-Generated Item Drafts in Clinical Assessment. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 172–182, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).