Open Generative Large Language Models for Galician

TL;DR

This paper introduces the first open-source generative large language models for Galician, trained with 1.3 billion parameters, aiming to reduce language bias and improve NLP access for minoritized languages.

Contribution

It presents two novel Galician-focused LLMs trained via continual pretraining, addressing resource scarcity and promoting linguistic diversity in NLP models.

Findings

Models show promising performance in evaluations

Human judgments and benchmark datasets support effectiveness

Highlights importance of linguistic diversity in LLMs

Abstract

Large language models (LLMs) have transformed natural language processing. Yet, their predominantly English-centric training has led to biases and performance disparities across languages. This imbalance marginalizes minoritized languages, making equitable access to NLP technologies more difficult for languages with lower resources, such as Galician. We present the first two generative LLMs focused on Galician to bridge this gap. These models, freely available as open-source resources, were trained using a GPT architecture with 1.3B parameters on a corpus of 2.1B words. Leveraging continual pretraining, we adapt to Galician two existing LLMs trained on larger corpora, thus mitigating the data constraints that would arise if the training were performed from scratch. The models were evaluated using human judgments and task-based datasets from standardized benchmarks. These evaluations reveal a promising performance, underscoring the importance of linguistic diversity in generative models.