Saved in:
Bibliographic Details
Main Authors: Singh, Amrita, Karaca, H. Suhan, Joshi, Aditya, Paik, Hye-young, Jiang, Jiaojiao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07849
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910246997327872
author Singh, Amrita
Karaca, H. Suhan
Joshi, Aditya
Paik, Hye-young
Jiang, Jiaojiao
author_facet Singh, Amrita
Karaca, H. Suhan
Joshi, Aditya
Paik, Hye-young
Jiang, Jiaojiao
contents Despite advances in legal NLP, no comprehensive evaluation of Transformer-based models customized for legal tasks (referred to as `legal-specific' models in this paper) exists for contract classification tasks. To address this gap, we present an evaluation of 13 legal-specific transformer-based models on 3 English-language contract classification tasks and compare them with 9 generalist models. The results show that legal-specific models consistently outperform generalist models, especially on tasks requiring nuanced legal understanding. They also help reduce misclassification of rare classes in imbalanced datasets. Legal-BERT and Contracts-BERT establish new SOTAs on two of the three tasks, despite having 69% fewer parameters than the best-performing generalist models. We also identify CaseLaw-BERT and LexLM as strong additional baselines for contract classification. Our results highlight the shortcomings of generalist models, emphasizing the need for domain-specific customization, particularly in the context of legal applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Customized vs. Generalist Transformer-based Models for Legal Contract Classification
Singh, Amrita
Karaca, H. Suhan
Joshi, Aditya
Paik, Hye-young
Jiang, Jiaojiao
Computation and Language
Despite advances in legal NLP, no comprehensive evaluation of Transformer-based models customized for legal tasks (referred to as `legal-specific' models in this paper) exists for contract classification tasks. To address this gap, we present an evaluation of 13 legal-specific transformer-based models on 3 English-language contract classification tasks and compare them with 9 generalist models. The results show that legal-specific models consistently outperform generalist models, especially on tasks requiring nuanced legal understanding. They also help reduce misclassification of rare classes in imbalanced datasets. Legal-BERT and Contracts-BERT establish new SOTAs on two of the three tasks, despite having 69% fewer parameters than the best-performing generalist models. We also identify CaseLaw-BERT and LexLM as strong additional baselines for contract classification. Our results highlight the shortcomings of generalist models, emphasizing the need for domain-specific customization, particularly in the context of legal applications.
title Evaluating Customized vs. Generalist Transformer-based Models for Legal Contract Classification
topic Computation and Language
url https://arxiv.org/abs/2508.07849