Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.01747 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911416183685120 |
|---|---|
| author | Choi, Hongseok Kim, Serynn Liermann, Wencke Seong, Jin Huang, Jin-Xia |
| author_facet | Choi, Hongseok Kim, Serynn Liermann, Wencke Seong, Jin Huang, Jin-Xia |
| contents | Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical adoption of robust AES systems. This study proposes a novel approach to enhance AES performance in both limited-data and full-data settings by introducing three key techniques. First, we introduce a Two-Stage fine-tuning strategy that leverages low-rank adaptations to better adapt an AES model to target prompt essays. Second, we introduce a Score Alignment technique to improve consistency between predicted and true score distributions. Third, we employ uncertainty-aware self-training using unlabeled data, effectively expanding the training set with pseudo-labeled samples while mitigating label noise propagation. We implement above three key techniques on DualBERT. We conduct extensive experiments on the ASAP++ dataset. As a result, in the 32-data setting, all three key techniques improve performance, and their integration achieves 91.2% of the full-data performance trained on approximately 1,000 labeled samples. In addition, the proposed Score Alignment technique consistently improves performance in both limited-data and full-data settings: e.g., it achieves state-of-the-art results in the full-data setting when integrated into DualBERT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01747 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training Choi, Hongseok Kim, Serynn Liermann, Wencke Seong, Jin Huang, Jin-Xia Computation and Language Machine Learning I.2.7 Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the extreme scarcity of labeled data severely limits the development and practical adoption of robust AES systems. This study proposes a novel approach to enhance AES performance in both limited-data and full-data settings by introducing three key techniques. First, we introduce a Two-Stage fine-tuning strategy that leverages low-rank adaptations to better adapt an AES model to target prompt essays. Second, we introduce a Score Alignment technique to improve consistency between predicted and true score distributions. Third, we employ uncertainty-aware self-training using unlabeled data, effectively expanding the training set with pseudo-labeled samples while mitigating label noise propagation. We implement above three key techniques on DualBERT. We conduct extensive experiments on the ASAP++ dataset. As a result, in the 32-data setting, all three key techniques improve performance, and their integration achieves 91.2% of the full-data performance trained on approximately 1,000 labeled samples. In addition, the proposed Score Alignment technique consistently improves performance in both limited-data and full-data settings: e.g., it achieves state-of-the-art results in the full-data setting when integrated into DualBERT. |
| title | Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training |
| topic | Computation and Language Machine Learning I.2.7 |
| url | https://arxiv.org/abs/2602.01747 |