Saved in:
Bibliographic Details
Main Authors: Fan, Kevin, Bialo, Jacquelyn A., Li, Hongli
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.08796
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915786566664192
author Fan, Kevin
Bialo, Jacquelyn A.
Li, Hongli
author_facet Fan, Kevin
Bialo, Jacquelyn A.
Li, Hongli
contents Constructing a Q-matrix is a critical but labor-intensive step in cognitive diagnostic modeling (CDM). This study investigates whether AI tools (i.e., general language models) can support Q-matrix development by comparing AI-generated Q-matrices with a validated Q-matrix from Li and Suen (2013) for a reading comprehension test. In May 2025, multiple AI models were provided with the same training materials as human experts. Agreement among AI-generated Q-matrices, the validated Q-matrix, and human raters' Q-matrices was assessed using Cohen's kappa. Results showed substantial variation across AI models, with Google Gemini 2.5 Pro achieving the highest agreement (Kappa = 0.63) with the validated Q-matrix, exceeding that of all human experts. A follow-up analysis in January 2026 using newer AI versions, however, revealed lower agreement with the validated Q-matrix. Implications and directions for future research are discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08796
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Use of AI Tools to Develop and Validate Q-Matrices
Fan, Kevin
Bialo, Jacquelyn A.
Li, Hongli
Artificial Intelligence
Computation and Language
Constructing a Q-matrix is a critical but labor-intensive step in cognitive diagnostic modeling (CDM). This study investigates whether AI tools (i.e., general language models) can support Q-matrix development by comparing AI-generated Q-matrices with a validated Q-matrix from Li and Suen (2013) for a reading comprehension test. In May 2025, multiple AI models were provided with the same training materials as human experts. Agreement among AI-generated Q-matrices, the validated Q-matrix, and human raters' Q-matrices was assessed using Cohen's kappa. Results showed substantial variation across AI models, with Google Gemini 2.5 Pro achieving the highest agreement (Kappa = 0.63) with the validated Q-matrix, exceeding that of all human experts. A follow-up analysis in January 2026 using newer AI versions, however, revealed lower agreement with the validated Q-matrix. Implications and directions for future research are discussed.
title The Use of AI Tools to Develop and Validate Q-Matrices
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2602.08796