{
 "id": "llm-jp/scaling-data-constrained-llms",
 "owner": "llm-jp",
 "name": "scaling-data-constrained-llms",
 "downloads": 375,
 "likes": 5,
 "last_modified": "2026-10-13T00:36:56.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{kiyomaru-etal-2026-scaling,\n    title = \"Scaling Data-Constrained Language Models with Synthetic Data\",\n    author = \"Kiyomaru, Hirokazu  and\n      Oda, Yusuke  and\n      Kodama, Takashi  and\n      Liu, Chaoran  and\n      Kawahara, Daisuke\",\n    editor = \"Demberg, Vera  and\n      Inui, Kentaro  and\n      Marquez, Llu{\\'i}s\",\n    booktitle = \"Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026\",\n    month = mar,\n    year = \"2026\",\n    address = \"Rabat, Morocco\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.findings-eacl.52/\",\n    pages = \"1002--1016\",\n    ISBN = \"979-8-89176-386-9\",\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "ea7f7e0eb67ea0f6e54f49e48d1436739b8d8910",
 "stated_evidence": "https://huggingface.co/datasets/llm-jp/scaling-data-constrained-llms/blob/ea7f7e0eb67ea0f6e54f49e48d1436739b8d8910/README.md",
 "file_evidence": "https://huggingface.co/datasets/llm-jp/scaling-data-constrained-llms/tree/ea7f7e0eb67ea0f6e54f49e48d1436739b8d8910",
 "card_nc": false
}