{
 "id": "mteb/KorHateSpeechMLClassification",
 "owner": "mteb",
 "name": "KorHateSpeechMLClassification",
 "downloads": 479,
 "likes": 0,
 "last_modified": "2026-02-24T21:19:13.000Z",
 "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-classification"
 ],
 "citation": "@inproceedings{lee-etal-2022-k,\n  address = {Gyeongju, Republic of Korea},\n  author = {Lee, Jean  and\nLim, Taejun  and\nLee, Heejun  and\nJo, Bogeun  and\nKim, Yangsok  and\nYoon, Heegeun  and\nHan, Soyeon Caren},\n  booktitle = {Proceedings of the 29th International Conference on Computational Linguistics},\n  month = oct,\n  pages = {3530--3538},\n  publisher = {International Committee on Computational Linguistics},\n  title = {K-{MH}a{S}: A Multi-label Hate Speech Detection Dataset in {K}orean Online News Comment},\n  url = {https://aclanthology.org/2022.coling-1.311},\n  year = {2022},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zh",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "9644ac13e57f6e3ec207247c013270b33494c326",
 "stated_evidence": "https://huggingface.co/datasets/mteb/KorHateSpeechMLClassification/blob/9644ac13e57f6e3ec207247c013270b33494c326/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/KorHateSpeechMLClassification/tree/9644ac13e57f6e3ec207247c013270b33494c326",
 "card_nc": false
}