Open Access

ARTICLE

Effective Token Masking Augmentation Using Term-Document Frequency for Language Model-Based Legal Case Classification

Ye-Chan Park¹, Mohd Asyraf Zulkifley², Bong-Soo Sohn³, Jaesung Lee^4,*

1 Department of Artificial Intelligence, Chung-Ang University, Seoul, 06974, Republic of Korea
2 Department of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi, 43600, Malaysia
3 School of Computer Science and Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea
4 AI/ML Innovation Research Center, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, 06974, Republic of Korea

* Corresponding Author: Jaesung Lee. Email:

Computers, Materials & Continua 2026, 87(1), 36 https://doi.org/10.32604/cmc.2025.074141

Received 03 October 2025; Accepted 20 November 2025; Issue published 10 February 2026

Abstract

Legal case classification involves the categorization of legal documents into predefined categories, which facilitates legal information retrieval and case management. However, real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains. This leads to biased model performance, in the form of high accuracy for overrepresented categories and underperformance for minority classes. To address this issue, in this study, we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms from the perspective of the legal domain. This approach enhances data diversity and improves the generalization capability of conventional models. Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models, validating the effectiveness of the proposed method in legal case classification.

---

Keywords

---