Igea: a Decoder-Only Language Model for Biomedical Text Generation in Italian

TL;DR

Igea is a novel decoder-only language model tailored for biomedical text generation in Italian, addressing the scarcity of domain-specific models for less-resourced languages and demonstrating strong performance across biomedical and general benchmarks.

Contribution

This paper introduces Igea, the first Italian biomedical decoder-only language model, built on Minerva, with multiple sizes, and evaluated on domain-specific and general benchmarks.

Findings

Igea performs well on biomedical corpora.

Igea retains general knowledge after domain training.

Models are efficient across three sizes.

Abstract

The development of domain-specific language models has significantly advanced natural language processing applications in various specialized fields, particularly in biomedicine. However, the focus has largely been on English-language models, leaving a gap for less-resourced languages such as Italian. This paper introduces Igea, the first decoder-only language model designed explicitly for biomedical text generation in Italian. Built on the Minerva model and continually pretrained on a diverse corpus of Italian medical texts, Igea is available in three model sizes: 350 million, 1 billion, and 3 billion parameters. The models aim to balance computational efficiency and performance, addressing the challenges of managing the peculiarities of medical terminology in Italian. We evaluate Igea using a mix of in-domain biomedical corpora and general-purpose benchmarks, highlighting its efficacy and retention of general knowledge even after the domain-specific training. This paper discusses the model's development and evaluation, providing a foundation for future advancements in Italian biomedical NLP.