@inproceedings{walsh-ivan-2026-quacks,
title = "It Quacks Like a Response: Evaluating Synthetically-Generated Responses in Assessment Research",
author = "Walsh, Cole and
Ivan, Rodica",
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.18/",
pages = "170--178",
ISBN = "979-8-9983004-0-0",
abstract = "This study evaluates synthetic open-response data generation for assessment development by using real response data as ground truth. It finds that conditioning LLM generation on actual test-taker responses improves fidelity and diversity, though synthetic responses still lack the full variation of real test-takers, limiting current psychometric utility."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="walsh-ivan-2026-quacks">
<titleInfo>
<title>It Quacks Like a Response: Evaluating Synthetically-Generated Responses in Assessment Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cole</namePart>
<namePart type="family">Walsh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodica</namePart>
<namePart type="family">Ivan</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>This study evaluates synthetic open-response data generation for assessment development by using real response data as ground truth. It finds that conditioning LLM generation on actual test-taker responses improves fidelity and diversity, though synthetic responses still lack the full variation of real test-takers, limiting current psychometric utility.</abstract>
<identifier type="citekey">walsh-ivan-2026-quacks</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-main.18/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>170</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T It Quacks Like a Response: Evaluating Synthetically-Generated Responses in Assessment Research
%A Walsh, Cole
%A Ivan, Rodica
%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 walsh-ivan-2026-quacks
%X This study evaluates synthetic open-response data generation for assessment development by using real response data as ground truth. It finds that conditioning LLM generation on actual test-taker responses improves fidelity and diversity, though synthetic responses still lack the full variation of real test-takers, limiting current psychometric utility.
%U https://aclanthology.org/2026.aimecon-main.18/
%P 170-178
Markdown (Informal)
[It Quacks Like a Response: Evaluating Synthetically-Generated Responses in Assessment Research](https://aclanthology.org/2026.aimecon-main.18/) (Walsh & Ivan, AIME-Con 2026)
ACL