Automatic Essay Scoring and Feedback Generation in Basque Language Learning

TL;DR

This paper presents a new dataset and models for automatic essay scoring and feedback in Basque, demonstrating that fine-tuned open-source models outperform proprietary systems in scoring accuracy and feedback quality.

Contribution

Introduces the first publicly available Basque AES dataset, fine-tunes open-source models for scoring and feedback, and proposes a novel evaluation methodology for feedback quality.

Findings

Fine-tuned Latxa model surpasses GPT-5 and Claude Sonnet 4.5 in scoring accuracy.

Encoder models are highly reliable for AES tasks.

The approach produces pedagogically meaningful feedback and identifies diverse error types.

Abstract

This paper introduces the first publicly available dataset for Automatic Essay Scoring (AES) and feedback generation in Basque, targeting the CEFR C1 proficiency level. The dataset comprises 3,200 essays from HABE, each annotated by expert evaluators with criterion specific scores covering correctness, richness, coherence, cohesion, and task alignment enriched with detailed feedback and error examples. We fine-tune open-source models, including RoBERTa-EusCrawl and Latxa 8B/70B, for both scoring and explanation generation. Our experiments show that encoder models remain highly reliable for AES, while supervised fine-tuning (SFT) of Latxa significantly enhances performance, surpassing state-of-the-art (SoTA) closed-source systems such as GPT-5 and Claude Sonnet 4.5 in scoring consistency and feedback quality. We also propose a novel evaluation methodology for assessing feedback generation, combining automatic consistency metrics with expert-based validation of extracted learner errors. Results demonstrate that the fine-tuned Latxa model produces criterion-aligned, pedagogically meaningful feedback and identifies a wider range of error types than proprietary models. This resource and benchmark establish a foundation for transparent, reproducible, and educationally grounded NLP research in low-resource languages such as Basque.