HiTZ Center develops Latxa, the largest language model for Basque

Feb 27, 2024

This first version developed by the HiTZ center, a LANGUNE member, will be essential for building chatbot-type tools for the general public.

Card image cap

A large language model, LLM, is an artificial intelligence model that uses machine learning techniques to understand and produce human language; it is based on the knowledge generated by massive data sets. Basque also has its own LLM: Latxa. It is based on the Meta's LLaMa models, and brings together between 7 and 70 billion model parameters. Today’s LLMs perform amazingly in well-resourced languages, such as those of ChatGPT or Bard for English. However, in the case of Basque and other poorly-resourced languages, its performance is close to random guessing. This increases the technological gap between well-resourced and poorly-resourced languages, at least as far as digital tools are concerned. Latxa was developed by the Langune member HiTZ Basque Centre for Language Technology (UPV/EHU) to overcome these limitations and promote the development of products, innovations and products in Basque based on the LLM. This work was supported by the Basque Government (within the IKER-GAITU project).

Further information

Related news

The UEU will be offering a postgraduate degree in Basque and Digitality during the 2024/2025 academic year

Jun 05, 2024

It will be an online postgraduate programme to train people wishing to promote Basque in the digital context.

ANETI AGM attended by TISA, Elhuyar and LANGUNE

May 31, 2024

On 23 May ANETI, the National Association of Translation and Interpreting Companies, held its Annual General Meeting in Barcelona.

Cases of high-impact use of Language Technologies

May 09, 2024

Langune, Emun and the HITZ centre conducted 17 interviews and received 282 responses to their questionnaire.