Beyond the Black Box: Interpretable Multi-Trait Essay Scoring with Trait-Aware Transformer
Electronics · 04.03.2026 · 15 (5) · 1066
DOI: 10.3390/electronics15051066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 04.03.2026. Verfasst von Xiaoyi Tang. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education of the People’s Republic of China (MOE) Project of Humanities and Social Sciences, University of Science and Technology Beijing Exploratory Project on AI-Enabled Education.
Abstract (Originalsprache)
The rapid advancement of automated essay scoring (AES) has been constrained by a representation bottleneck, where monolithic models collapse diverse facets of writing constructs into a single, uninterpretable signal, undermining the pedagogical value of multi-dimensional rating traits. To address this limitation, the RoBERTa-based Trait-Aware Transformer (RoBERTa-TAT) is introduced. This architectural reframing replaces unified pooling with parallel, trait-specific attention streams, preserving and disentangling critical features such as conceptual depth and mechanical precision. Tested on the ASAP Dataset-7, RoBERTa-TAT attains a new state-of-the-art Quadratic Weighted Kappa (QWK) of 0.936, outperforming sequential baselines and conventional Transformer variants. Beyond gains in accuracy, this trait-specialized architecture recasts scoring from a black-box prediction into a transparent diagnostic tool, enabling actionable, fine-grained feedback at different rating traits. High-resolution inspection reveals that the model’s internal representations correlate with specific linguistic markers—such as discourse connectives for organization—suggesting a degree of structural alignment with expert judgment. By aligning high-capacity representation learning with the granular demands of formative assessment, RoBERTa-TAT provides a practical, interpretable blueprint for deploying accountable AI in education and broadening access to expert diagnostic insight.
Förderung
- Ministry of Education of the People’s Republic of China (MOE) Project of Humanities and Social Sciences
- University of Science and Technology Beijing Exploratory Project on AI-Enabled Education
Zitieren
APA
Tang, X. (2026). Beyond the Black Box: Interpretable Multi-Trait Essay Scoring with Trait-Aware Transformer. Electronics, 15(5), 1066. https://doi.org/10.3390/electronics15051066
Vancouver
Tang X. Beyond the Black Box: Interpretable Multi-Trait Essay Scoring with Trait-Aware Transformer. Electronics. 2026;15(5):1066. doi:10.3390/electronics15051066
BibTeX
@article{Tang2026,
author = {Tang, Xiaoyi},
title = {Beyond the Black Box: Interpretable Multi-Trait Essay Scoring with Trait-Aware Transformer},
journal = {Electronics},
year = {2026},
volume = {15},
number = {5},
pages = {1066},
doi = {10.3390/electronics15051066}
}
EUVIMED