Year: 2026
Type: conference-paper
Abstract: Beyond performance, model transparency is a crucial factor in Automated Essay Scoring, yet current systems often lack explainability, limiting their pedagogical value and users' trust.Existing explainability methods, such as gradient-based attribution or featureimportance approaches, either produce counterintuitive explanations or are too complex for classroom use.To address this limitation, we make use of fine-grained prediction at the sentence level as a way to enhance explainability.We propose ablation strategies to derive sentence-level pseudo scores from essay-level gold scores and use them to train sentence-level models.We evaluate their performance against essay-level baselines on two datasets (ASAP and MEWS), and compare their sentence-level output to a human baseline.Results indicate a trade-off between essay-level performance and sentence-level granularity.For the language quality trait, most sentence-level models achieve performance comparable to the essaylevel baseline, whereas for content, the approach yields more positive results on prompts with shorter student texts.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7166894766