Explainable AI for education: Enhancing essay scoring via rubric-aligned chain-of-thought prompting
Document Type
Article
Publication Date
6-1-2026
Abstract
Automated essay scoring (AES) systems increasingly leverage fine-tuned large language models (LLMs) to enhance scoring accuracy and feedback generation. However, current LLM-based AES approaches often lack interpretability and consistent alignment with human scoring rubrics, limiting their practical adoption in educational settings. This study proposes QwenScore+, a novel framework that integrates rubric-aware Chain-of-Thought (CoT) prompting with reinforcement learning from human feedback (RLHF) to improve the transparency, quality and educational alignment of automated feedback. QwenScore+ is evaluated on a proprietary IELTS writing dataset comprising over 5000 essays annotated with trait-level scores and expert-written feedback. Experimental results demonstrate that QwenScore+ significantly outperforms strong baselines such as BERT, GPT-3.5 and GPT-4 in feedback generation, achieving higher BLEU, ROUGE-L and cosine similarity scores, alongside improvements in trait-level scoring measured by quadratic weighted kappa (QWK). Furthermore, rubric-aligned CoT prompting enables the generation of feedback that better mirrors human reasoning patterns, as confirmed through automatic metrics and human evaluations. These findings highlight the potential of combining explainable reasoning strategies with human-aligned reward optimization to develop more transparent, reliable and pedagogically valuable AES systems for real-world applications.
Keywords
Automated essay scoring (AES), chain-of-thought prompting, explainability, large language models (LLMs), rubric alignment
Publication Title
International Journal of Modern Physics C
ISSN
0129-1831
DOI
10.1142/S0129183125420136
Recommended Citation
Xu, Wenbo; Kassim, M. S.S.; Hoo, Wai Lam; Yang, Wudao; and Xu, Tianrong, "Explainable AI for education: Enhancing essay scoring via rubric-aligned chain-of-thought prompting" (2026). Research Publications (2026 to 2030). 599.
https://knova.um.edu.my/research_publications_2026_2030/599
Volume
37
Issue
6