Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918385258856448 |
|---|---|
| author | Sainz, Oscar Perez, Naiara Etxaniz, Julen de Landa, Joseba Fernandez Aldabe, Itziar García-Ferrero, Iker Zabala, Aimar Azurmendi, Ekhi Rigau, German Agirre, Eneko Artetxe, Mikel Soroa, Aitor |
| author_facet | Sainz, Oscar Perez, Naiara Etxaniz, Julen de Landa, Joseba Fernandez Aldabe, Itziar García-Ferrero, Iker Zabala, Aimar Azurmendi, Ekhi Rigau, German Agirre, Eneko Artetxe, Mikel Soroa, Aitor |
| contents | Instructing language models with user intent requires large instruction datasets, which are only available for a limited set of languages. In this paper, we explore alternatives to conventional instruction adaptation pipelines in low-resource scenarios. We assume a realistic scenario for low-resource languages, where only the following are available: corpora in the target language, existing open-weight multilingual base and instructed backbone LLMs, and synthetically generated instructions sampled from the instructed backbone. We present a comprehensive set of experiments for Basque that systematically study different combinations of these components evaluated on benchmarks and human preferences from 1,680 participants. Our conclusions show that target language corpora are essential, with synthetic instructions yielding robust models, and, most importantly, that using as backbone an instruction-tuned model outperforms using a base non-instructed model. Scaling up to Llama 3.1 Instruct 70B as backbone, our model comes near frontier models of much larger sizes for Basque, without using any Basque instructions. We release code, models, instruction datasets, and human preferences to support full reproducibility in future research on low-resource language adaptation. https://github.com/hitz-zentroa/latxa-instruct |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque Sainz, Oscar Perez, Naiara Etxaniz, Julen de Landa, Joseba Fernandez Aldabe, Itziar García-Ferrero, Iker Zabala, Aimar Azurmendi, Ekhi Rigau, German Agirre, Eneko Artetxe, Mikel Soroa, Aitor Computation and Language Instructing language models with user intent requires large instruction datasets, which are only available for a limited set of languages. In this paper, we explore alternatives to conventional instruction adaptation pipelines in low-resource scenarios. We assume a realistic scenario for low-resource languages, where only the following are available: corpora in the target language, existing open-weight multilingual base and instructed backbone LLMs, and synthetically generated instructions sampled from the instructed backbone. We present a comprehensive set of experiments for Basque that systematically study different combinations of these components evaluated on benchmarks and human preferences from 1,680 participants. Our conclusions show that target language corpora are essential, with synthetic instructions yielding robust models, and, most importantly, that using as backbone an instruction-tuned model outperforms using a base non-instructed model. Scaling up to Llama 3.1 Instruct 70B as backbone, our model comes near frontier models of much larger sizes for Basque, without using any Basque instructions. We release code, models, instruction datasets, and human preferences to support full reproducibility in future research on low-resource language adaptation. https://github.com/hitz-zentroa/latxa-instruct |
| title | Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.07597 |