@inproceedings{sachdeva-park-2025-leveraging,
title = "Leveraging {LLM}s for Cognitive Skill Mapping in {TIMSS} Mathematics Assessment",
author = "Sachdeva, Ruchi J and
Park, Jung Yeon",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress",
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-wip.28/",
pages = "223--228",
ISBN = "979-8-218-84229-1",
abstract = "This study evaluates ChatGPT-4{'}s potential to support validation of Q-matrices and analysis of complex skill{--}item interactions. By comparing its outputs to expert benchmarks, we assess accuracy, consistency, and limitations, offering insights into how large language models can augment expert judgment in diagnostic assessment and cognitive skill mapping."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sachdeva-park-2025-leveraging">
<titleInfo>
<title>Leveraging LLMs for Cognitive Skill Mapping in TIMSS Mathematics Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruchi</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Sachdeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jung</namePart>
<namePart type="given">Yeon</namePart>
<namePart type="family">Park</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): Works in Progress</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">979-8-218-84229-1</identifier>
</relatedItem>
<abstract>This study evaluates ChatGPT-4’s potential to support validation of Q-matrices and analysis of complex skill–item interactions. By comparing its outputs to expert benchmarks, we assess accuracy, consistency, and limitations, offering insights into how large language models can augment expert judgment in diagnostic assessment and cognitive skill mapping.</abstract>
<identifier type="citekey">sachdeva-park-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-wip.28/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>223</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging LLMs for Cognitive Skill Mapping in TIMSS Mathematics Assessment
%A Sachdeva, Ruchi J.
%A Park, Jung Yeon
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84229-1
%F sachdeva-park-2025-leveraging
%X This study evaluates ChatGPT-4’s potential to support validation of Q-matrices and analysis of complex skill–item interactions. By comparing its outputs to expert benchmarks, we assess accuracy, consistency, and limitations, offering insights into how large language models can augment expert judgment in diagnostic assessment and cognitive skill mapping.
%U https://aclanthology.org/2025.aimecon-wip.28/
%P 223-228
Markdown (Informal)
[Leveraging LLMs for Cognitive Skill Mapping in TIMSS Mathematics Assessment](https://aclanthology.org/2025.aimecon-wip.28/) (Sachdeva & Park, AIME-Con 2025)
ACL
- Ruchi J Sachdeva and Jung Yeon Park. 2025. Leveraging LLMs for Cognitive Skill Mapping in TIMSS Mathematics Assessment. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 223–228, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).