arXiv 2602.017472026-02cs.CLcs.LG

通过三种技术增强自动作文评分：两阶段微调、评分对齐和自训练

Enhancing Automated Essay Scoring With Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training

Electronics and Telecommunications Research Institute（电子电信研究院）；Hankuk University of Foreign Studies（韩国外国语大学）

Hongseok Choi, Serynn Kim, Wencke Liermann, Jin Seong, Jin-Xia Huang

备注：: 16 pages, 5 figures, 11 tables. Published in IEEE Access (open access, CC BY 4.0)
发表信息：: IEEE Access, vol. 14, pp. 117193-117208, 2026
DOI：: 10.1109/ACCESS.2026.3718177

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究通过两阶段微调、评分对齐和自训练三种技术提升自动作文评分性能，实现91.2%的完整数据表现。

摘要：

自动作文评分（AES）在教育中发挥着关键作用，通过提供可扩展和高效的评估工具。然而，在现实环境中，标记数据的极端稀缺严重限制了稳健AES系统的发展和实际应用。本研究提出了一种新的方法，通过引入三种关键技术来增强AES在有限数据和完整数据设置下的性能。首先，我们引入了一种两阶段微调策略，利用低秩适应来更好地适应AES模型到目标提示作文。其次，我们引入了评分对齐技术，以提高预测和真实分数分布之间的一致性。第三，我们采用基于不确定性的自训练方法，利用未标记数据，有效地扩展训练集，同时减少标签噪声的传播。我们将在DualBERT上实现上述三种关键技术。我们在ASAP++数据集上进行了广泛的实验。结果表明，在32数据设置下，三种关键技术均提升了性能，其整合达到了在约1000个标记样本上训练的完整数据性能的91.2%。此外，所提出的评分对齐技术在有限数据和完整数据设置中均一致提升了性能：例如，当将其整合到DualBERT中时，在完整数据设置下实现了最先进的结果。

英文摘要：

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 the above three key techniques on DualBERT. We conduct extensive experiments on the ASAP++ dataset, and additionally evaluate the proposed techniques on two other datasets, TOEFL11 and ELLIPSE, to examine their generalizability. In the 32-data setting on ASAP++, 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 on ASAP++ when integrated into DualBERT.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文