{
 "id": "slovak-nlp/sklep",
 "owner": "slovak-nlp",
 "name": "sklep",
 "downloads": 655,
 "likes": 7,
 "last_modified": "2026-03-03T13:12:03.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "text-classification",
  "token-classification"
 ],
 "citation": "@inproceedings{suppa-etal-2025-sklep,\n    title = \"sk{LEP}: A {S}lovak General Language Understanding Benchmark\",\n    author = \"Suppa, Marek  and\n      Ridzik, Andrej  and\n      Hl{\\'a}dek, Daniel  and\n      Jav{\\r{u}}rek, Tom{\\'a}{\\v{s}}  and\n      Ondrejov{\\'a}, Vikt{\\'o}ria  and\n      S{\\'a}sikov{\\'a}, Krist{\\'i}na  and\n      Tamajka, Martin  and\n      Simko, Marian\",\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.1371/\",\n    pages = \"26716--26743\",\n    ISBN = \"979-8-89176-256-5\",\n    abstract = \"In this work, we introduce skLEP, the first comprehensive benchmark specifically designed for evaluating Slovak natural language understanding (NLU) models. We have compiled skLEP to encompass nine diverse tasks that span token-level, sentence-pair, and document-level challenges, thereby offering a thorough assessment of model capabilities. To create this benchmark, we curated new, original datasets tailored for Slovak and meticulously translated established English NLU resources. Within this paper, we also present the first systematic and extensive evaluation of a wide array of Slovak-specific, multilingual, and English pre-trained language",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "10549a8c63542e6a0db4fcf5fcdc29b3e1b8c4e9",
 "stated_evidence": "https://huggingface.co/datasets/slovak-nlp/sklep/blob/10549a8c63542e6a0db4fcf5fcdc29b3e1b8c4e9/README.md",
 "file_evidence": "https://huggingface.co/datasets/slovak-nlp/sklep/tree/10549a8c63542e6a0db4fcf5fcdc29b3e1b8c4e9",
 "card_nc": false
}