{
 "id": "proxectonos/cpt_instruction_datasets",
 "owner": "proxectonos",
 "name": "cpt_instruction_datasets",
 "downloads": 461,
 "likes": 1,
 "last_modified": "2026-04-21T16:07:09.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text-classification",
  "token-classification",
  "question-answering",
  "summarization",
  "translation"
 ],
 "citation": "@inproceedings{rodriguez-etal-2025-continued,\n    title = \"Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A {G}alician Case Study\",\n    author = \"Rodr{\\'i}guez, Pablo  and\n      Su{\\'a}rez, Silvia Paniagua  and\n      Gamallo, Pablo  and\n      Docio, Susana Sotelo\",\n    editor = \"Che, Wanxiang  and\n      Nabende, Joyce  and\n      Shutova, Ekaterina  and\n      Pilehvar, Mohammad Taher\",\n    booktitle = \"Findings of the Association for Computational Linguistics: ACL 2025\",\n    month = jul,\n    year = \"2025\",\n    address = \"Vienna, Austria\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.findings-acl.240/\",\n    doi = \"10.18653/v1/2025.findings-acl.240\",\n    pages = \"4622--4637\",\n    ISBN = \"979-8-89176-256-5\",\n    abstract = \"Recent advances in Large Language Models (LLMs) have led to remarkable improvements in language understanding and text generation. However, challenges remain in enhancing their performance for underrepresented languages, ensuring continual learning without catastrophic forgetting, and developing robust evaluation methodologies. This work addresses these issues by investigating the impact of Continued Pretraining (CPT) on multilingual models and proposing a comprehensive evaluation framework for LLMs, focusing on the case of Galician language. Our first contribution explores CPT strategies for languages with limited representation in multilingual models. We analyze",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "1130404291799e1463d467510a33c741e471d00d",
 "stated_evidence": "https://huggingface.co/datasets/proxectonos/cpt_instruction_datasets/blob/1130404291799e1463d467510a33c741e471d00d/README.md",
 "file_evidence": "https://huggingface.co/datasets/proxectonos/cpt_instruction_datasets/tree/1130404291799e1463d467510a33c741e471d00d",
 "card_nc": false
}