UCCIX: Irish-eXcellence Large Language Model
This work addresses the preservation and promotion of the Irish language and culture in the digital era, with potential applications for other indigenous languages, though it is incremental as it adapts existing methods to a new domain.
The paper tackles the underrepresentation of extremely low-resource languages like Irish in large language models by developing UCCIX, an open-source Irish-based LLM that achieves up to 12% performance improvement on Irish language tasks compared to larger models.
The development of Large Language Models (LLMs) has predominantly focused on high-resource languages, leaving extremely low-resource languages like Irish with limited representation. This work presents UCCIX, a pioneering effort on the development of an open-source Irish-based LLM. We propose a novel framework for continued pre-training of LLMs specifically adapted for extremely low-resource languages, requiring only a fraction of the textual data typically needed for training LLMs according to scaling laws. Our model, based on Llama 2-13B, outperforms much larger models on Irish language tasks with up to 12% performance improvement, showcasing the effectiveness and efficiency of our approach. We also contribute comprehensive Irish benchmarking datasets, including IrishQA, a question-answering dataset, and Irish version of MT-bench. These datasets enable rigorous evaluation and facilitate future research in Irish LLM systems. Our work aims to preserve and promote the Irish language, knowledge, and culture of Ireland in the digital era while providing a framework for adapting LLMs to other indigenous languages.