{
 "id": "cis-lmu/Glot500",
 "owner": "cis-lmu",
 "name": "Glot500",
 "downloads": 18989,
 "likes": 43,
 "last_modified": "2025-12-10T11:16:21.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "license",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{imanigooghari-etal-2023-glot500,\n    title = \"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages\",\n    author = {ImaniGooghari, Ayyoob  and\n      Lin, Peiqin  and\n      Kargaran, Amir Hossein  and\n      Severini, Silvia  and\n      Jalili Sabet, Masoud  and\n      Kassner, Nora  and\n      Ma, Chunlan  and\n      Schmid, Helmut  and\n      Martins, Andr{\\'e}  and\n      Yvon, Fran{\\c{c}}ois  and\n      Sch{\\\"u}tze, Hinrich},\n    editor = \"Rogers, Anna  and\n      Boyd-Graber, Jordan  and\n      Okazaki, Naoaki\",\n    booktitle = \"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2023\",\n    address = \"Toronto, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.acl-long.61\",\n    doi = \"10.18653/v1/2023.acl-long.61\",\n    pages = \"1082--1117\",\n    abstract = \"The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we create, through continued pretraining, Glot500-m, an LLM that covers 511 predominantly low-resource languages. An important part of this effort is to collect and clean Glot500-c, a corpus that covers these 511 languages and allows us to train Glot500-m. We evaluate Glot500-m on five diverse tasks across these languages. We observe large improvements for both high-resource",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "f7b3e9d11a7e974ec0d021342cd8b41fd67510c1",
 "stated_evidence": "https://huggingface.co/datasets/cis-lmu/Glot500/blob/f7b3e9d11a7e974ec0d021342cd8b41fd67510c1/README.md",
 "file_evidence": "https://huggingface.co/datasets/cis-lmu/Glot500/blob/f7b3e9d11a7e974ec0d021342cd8b41fd67510c1/LICENSE",
 "card_nc": false
}