{
 "id": "uonlp/CulturaX",
 "owner": "uonlp",
 "name": "CulturaX",
 "downloads": 25647,
 "likes": 706,
 "last_modified": "2024-12-16T17:24:53.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "citation": "@inproceedings{nguyen-etal-2024-culturax,\n    title = \"{C}ultura{X}: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages\",\n    author = \"Nguyen, Thuat  and\n      Nguyen, Chien Van  and\n      Lai, Viet Dac  and\n      Man, Hieu  and\n      Ngo, Nghia Trung  and\n      Dernoncourt, Franck  and\n      Rossi, Ryan A.  and\n      Nguyen, Thien Huu\",\n    editor = \"Calzolari, Nicoletta  and\n      Kan, Min-Yen  and\n      Hoste, Veronique  and\n      Lenci, Alessandro  and\n      Sakti, Sakriani  and\n      Xue, Nianwen\",\n    booktitle = \"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)\",\n    month = may,\n    year = \"2024\",\n    address = \"Torino, Italia\",\n    publisher = \"ELRA and ICCL\",\n    url = \"https://aclanthology.org/2024.lrec-main.377\",\n    pages = \"4226--4237\",\n    abstract = \"Extensive training datasets represent one of the important factors for the impressive learning capabilities of large language models (LLMs). However, these training datasets for current LLMs, especially the recent state-of-the-art models, are often not fully disclosed. Creating training data for high-performing LLMs involves extensive cleaning and deduplication to ensure the necessary level of quality. The lack of transparency for training data has thus hampered research on attributing and addressing hallucination and bias issues in LLMs, hindering replication efforts and further advancem",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata."
}