Subtrait (latent-trait components) assessment presents a promising path toward enhancing transparency of automated writing scores. We prototype explainability and subtrait scoring with generative language models and show modest correlation between human subtrait and trait scores, and between automated and human subtrait scores. Our approach provides details to demystify scores for educators and students.
@article{arxiv.2509.08345,
title = {Toward Subtrait-Level Model Explainability in Automated Writing Evaluation},
author = {Alejandro Andrade-Lotero and Lee Becker and Joshua Southerland and Scott Hellman},
journal= {arXiv preprint arXiv:2509.08345},
year = {2025}
}
Comments
Accepted to National Council on Measurement in Education (NCME) 2025 Annual Meeting