A Preliminary Semantic Screen for IRT Local Dependence

Qian Shen


Abstract
This work-in-progress study examines whether sentence embeddings can flag item pairs at risk for local dependence in multidimensional IRT. Using a 50-item personality inventory, preliminary analysis link semantic similarity to residual item-pair dependence. Future work will test robustness across larger samples, additional datasets, and alternative diagnostics.
Anthology ID:
2026.aimecon-wip.2
Volume:
Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress
Month:
October
Year:
2026
Address:
Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
Editors:
Joshua Wilson, Christopher Ormerod, Magdalen Beiting-Parrish
Venue:
AIME-Con
SIG:
Publisher:
National Council on Measurement in Education (NCME)
Note:
Pages:
9–16
Language:
URL:
https://aclanthology.org/2026.aimecon-wip.2/
DOI:
Bibkey:
Cite (ACL):
Qian Shen. 2026. A Preliminary Semantic Screen for IRT Local Dependence. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Works in Progress, pages 9–16, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).
Cite (Informal):
A Preliminary Semantic Screen for IRT Local Dependence (Shen, AIME-Con 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.aimecon-wip.2.pdf