Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque
This addresses the gap in AI capabilities for underrepresented languages like Basque, though it is incremental as it applies existing methods to a new language context.
This work tackled the problem of developing instruction-following large language models for low-resource languages, specifically Basque, by analyzing strategies like continual pre-training and instruction tuning, resulting in a 12-point improvement in natural language understanding and a 24-point improvement in instruction-following performance, establishing new state-of-the-art models.
Large language models (LLMs) are typically optimized for resource-rich languages like English, exacerbating the gap between high-resource and underrepresented languages. This work presents a detailed analysis of strategies for developing a model capable of following instructions in a low-resource language, specifically Basque, by focusing on three key stages: pre-training, instruction tuning, and alignment with human preferences. Our findings demonstrate that continual pre-training with a high-quality Basque corpus of around 600 million words improves natural language understanding (NLU) of the foundational model by over 12 points. Moreover, instruction tuning and human preference alignment using automatically translated datasets proved highly effective, resulting in a 24-point improvement in instruction-following performance. The resulting models, Llama-eus-8B and Llama-eus-8B-instruct, establish a new state-of-the-art for Basque in the sub-10B parameter category.