{
 "id": "HPLT/HPLT3.0",
 "owner": "HPLT",
 "name": "HPLT3.0",
 "downloads": 307,
 "likes": 24,
 "last_modified": "2026-07-08T12:37:21.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "fill-mask",
  "text-generation"
 ],
 "citation": "@inproceedings{oepen-etal-2026-very,\n  title = {HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models},\n  author = {Oepen, Stephan and Arefyev, Nikolay and Aulamo, Mikko and Bañón, Marta and Buljan, Maja and Burchell, Laurie V. and Charpentier, Lucas Georges Gabriel and Chen, Pinzhen and Fedorova, Mariia and Gibert, Ona de and Haddow, Barry and Hajič, Jan and Helcl, Jindrich and Kutuzov, Andrey and Laippala, Veronika and Li, Zihao and Malik, Bhavitvya and Mikhailov, Vladislav and Myntti, Amanda and O'Brien, Dayyán and Polakova, Lucie and Ramírez-Sánchez, Gema and Siewert, Janine and Stepachev, Pavel and Tiedemann, Joerg and Vahtola, Teemu and Varis, Dusan and Vitiugin, Fedor and Zaragoza, Jaume},\n  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)},\n  month = {May},\n  year = {2026},\n  pages = {1409--1434},\n  address = {Palma, Mallorca, Spain},\n  publisher = {European Language Resources Association (ELRA)},\n  editor = {Piperidis, Stelios and Bel, Núria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},\n  doi = {10.63317/25xbdofco9od},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "3394d6ba8dae4da834e3b11771daf95028a960b1",
 "stated_evidence": "https://huggingface.co/datasets/HPLT/HPLT3.0/blob/3394d6ba8dae4da834e3b11771daf95028a960b1/README.md",
 "file_evidence": "https://huggingface.co/datasets/HPLT/HPLT3.0/tree/3394d6ba8dae4da834e3b11771daf95028a960b1",
 "card_nc": false
}