From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring
This research provides the first unified empirical comparison of modern LLM-based AES strategies for English L2, offering valuable insights for educators and developers in auto-grading writing tasks.
This study compares four major LLM-based Automated Essay Scoring (AES) paradigms on IELTS Writing Task 2 for English as a Second Language (L2) writing. The best configuration, integrating k-SFT and RAG, achieved an F1-Score of 93%, demonstrating strong overall results.
Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing. To bridge this gap, we presents a comprehensive comparison of major LLM-based AES paradigms on IELTS Writing Task~2. On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and Retrieval-Augmented Generation (RAG), and (iv) Supervised Fine-Tuning combined with Direct Preference Optimization (DPO) and RAG. Our results reveal clear accuracy-cost-robustness trade-offs across methods, the best configuration, integrating k-SFT and RAG, achieves the strongest overall results with F1-Score 93%. This study offers the first unified empirical comparison of modern LLM-based AES strategies for English L2, promising potential in auto-grading writing tasks. Code is public at https://github.com/MinhNguyenDS/LLM_AES-EnL2