Salvato in:
Dettagli Bibliografici
Autori principali: Andrade-Lotero, Alejandro, Becker, Lee, Southerland, Joshua, Hellman, Scott
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.08345
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914031259877376
author Andrade-Lotero, Alejandro
Becker, Lee
Southerland, Joshua
Hellman, Scott
author_facet Andrade-Lotero, Alejandro
Becker, Lee
Southerland, Joshua
Hellman, Scott
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08345
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Subtrait-Level Model Explainability in Automated Writing Evaluation
Andrade-Lotero, Alejandro
Becker, Lee
Southerland, Joshua
Hellman, Scott
Computation and Language
Artificial Intelligence
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.
title Toward Subtrait-Level Model Explainability in Automated Writing Evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.08345