{
 "id": "HiTZ/safety-SeGa",
 "owner": "HiTZ",
 "name": "safety-SeGa",
 "downloads": 61,
 "likes": 0,
 "last_modified": "2026-07-24T08:02:22.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{sainz-etal-2025-instructing,\n    title = \"Instructing Large Language Models for Low-Resource Languages: A Systematic Study for {B}asque\",\n    author = \"Sainz, Oscar  and\n      Perez, Naiara  and\n      Etxaniz, Julen  and\n      Fernandez de Landa, Joseba  and\n      Aldabe, Itziar  and\n      Garc{\\'i}a-Ferrero, Iker  and\n      Zabala, Aimar  and\n      Azurmendi, Ekhi  and\n      Rigau, German  and\n      Agirre, Eneko  and\n      Artetxe, Mikel  and\n      Soroa, Aitor\",\n    editor = \"Christodoulopoulos, Christos  and\n      Chakraborty, Tanmoy  and\n      Rose, Carolyn  and\n      Peng, Violet\",\n    booktitle = \"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou, China\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.emnlp-main.1484/\",\n    doi = \"10.18653/v1/2025.emnlp-main.1484\",\n    pages = \"29124--29148\",\n    ISBN = \"979-8-89176-332-6\",\n    abstract = \"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 ge",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "c9412d80d30a1fe97a1acfe516995bbe3dd42028",
 "stated_evidence": "https://huggingface.co/datasets/HiTZ/safety-SeGa/blob/c9412d80d30a1fe97a1acfe516995bbe3dd42028/README.md",
 "file_evidence": "https://huggingface.co/datasets/HiTZ/safety-SeGa/tree/c9412d80d30a1fe97a1acfe516995bbe3dd42028",
 "card_nc": false
}