Workshop: Using AI and National Large Language Models to Advance Macedonian Language Capabilities

The “Using AI and National Large Language Models to Advance Macedonian Language Capabilities” Workshop is designed as an interactive event dedicated to the development of foundational artificial intelligence technologies that strengthen and expand the digital capabilities of the Macedonian language. It highlights the scientific and engineering efforts behind the creation of national large language models (LLMs), providing the technological foundation for trustworthy, high-quality AI systems tailored to the linguistic, cultural, and societal needs of North Macedonia.

The workshop will bring together people of various backgrounds to discuss their current and future work on the topic, as well as establish the necessary collaborations to further our common goals:

– Collection and curation of high-quality Macedonian language datasets
– Development of tokenizer technologies adapted to the Macedonian language
– Creation of LLMs for the Macedonian language and their evaluation on multiple criteria

The workshop will also demonstrate how national large language models can serve as strategic digital infrastructure, enabling the development of intelligent applications for education, research, public administration, cultural heritage preservation, and industry, while ensuring that the Macedonian language remains fully represented in the next generation of artificial intelligence technologies.