The Large Language Model GreekLegalRoBERTa

TL;DR

This paper introduces GreekLegalRoBERTa, a set of large language models trained on Greek legal texts that outperform existing models in legal NLP tasks, advancing domain-specific NLP for low-resource languages.

Contribution

The paper presents four new GreekLegalRoBERTa models trained on Greek legal and nonlegal texts, demonstrating superior performance over existing Greek legal language models.

Findings

Models outperform GreekLegalBERT, Greek-LegalBERT-v2, and GreekBERT in legal NLP tasks.

Models achieve higher accuracy in named entity recognition and legal topic classification.

Work advances NLP for Greek, a low-resource language, in legal domain.

Abstract

We develop four versions of GreekLegalRoBERTa, which are four large language models trained on Greek legal and nonlegal text. We show that our models surpass the performance of GreekLegalBERT, Greek- LegalBERT-v2, and GreekBERT in two tasks involving Greek legal documents: named entity recognition and multi-class legal topic classification. We view our work as a contribution to the study of domain-specific NLP tasks in low-resource languages, like Greek, using modern NLP techniques and methodologies.