@inproceedings{kim-2026-reproducible,
title = "How Reproducible Are {LLM}-Generated {Q}-Matrices? Evidence from Downstream Classification",
author = "Kim, Minkwon",
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.73/",
pages = "649--655",
ISBN = "979-8-9983004-0-0",
abstract = "Regenerating LLM Q-matrices ten times per model on TIMSS 2011 items, we find two runs of the same model reassign 61{--}88{\%} of student mastery profiles. Greedy decoding removes this instability; disagreement with expert judgment (63{--}76{\%}) survives. Majority voting fixes neither. Report distributions, not single runs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-2026-reproducible">
<titleInfo>
<title>How Reproducible Are LLM-Generated Q-Matrices? Evidence from Downstream Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minkwon</namePart>
<namePart type="family">Kim</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>Regenerating LLM Q-matrices ten times per model on TIMSS 2011 items, we find two runs of the same model reassign 61–88% of student mastery profiles. Greedy decoding removes this instability; disagreement with expert judgment (63–76%) survives. Majority voting fixes neither. Report distributions, not single runs.</abstract>
<identifier type="citekey">kim-2026-reproducible</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-main.73/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>649</start>
<end>655</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Reproducible Are LLM-Generated Q-Matrices? Evidence from Downstream Classification
%A Kim, Minkwon
%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-2026-reproducible
%X Regenerating LLM Q-matrices ten times per model on TIMSS 2011 items, we find two runs of the same model reassign 61–88% of student mastery profiles. Greedy decoding removes this instability; disagreement with expert judgment (63–76%) survives. Majority voting fixes neither. Report distributions, not single runs.
%U https://aclanthology.org/2026.aimecon-main.73/
%P 649-655
Markdown (Informal)
[How Reproducible Are LLM-Generated Q-Matrices? Evidence from Downstream Classification](https://aclanthology.org/2026.aimecon-main.73/) (Kim, AIME-Con 2026)
ACL