{
 "id": "tafseer-nayeem/KidLM-corpus",
 "owner": "tafseer-nayeem",
 "name": "KidLM-corpus",
 "downloads": 155,
 "likes": 2,
 "last_modified": "2025-10-06T05:51:51.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{nayeem-rafiei-2024-kidlm,\n    title = \"{K}id{LM}: Advancing Language Models for Children {--} Early Insights and Future Directions\",\n    author = \"Nayeem, Mir Tafseer  and\n      Rafiei, Davood\",\n    editor = \"Al-Onaizan, Yaser  and\n      Bansal, Mohit  and\n      Chen, Yun-Nung\",\n    booktitle = \"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.emnlp-main.277\",\n    pages = \"4813--4836\",\n    abstract = \"Recent studies highlight the potential of large language models in creating educational tools for children, yet significant challenges remain in maintaining key child-specific properties such as linguistic nuances, cognitive needs, and safety standards. In this paper, we explore foundational steps toward the development of child-specific language models, emphasizing the necessity of high-quality pre-training data. We introduce a novel user-centric data collection pipeline that involves gathering and validating a corpus specifically written for and sometimes by children. Additionally, we propose a new training objective, Stratified Masking, which dynamically adjusts masking probabilities based on our domain-specific child language data, enabling models to prioritize vocabulary and concepts more suitable for children. Experimental evaluations demonstrate ",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "3198df885fbba5ba41364c8f3d4c52e753173f0f",
 "stated_evidence": "https://huggingface.co/datasets/tafseer-nayeem/KidLM-corpus/blob/3198df885fbba5ba41364c8f3d4c52e753173f0f/README.md",
 "file_evidence": "https://huggingface.co/datasets/tafseer-nayeem/KidLM-corpus/tree/3198df885fbba5ba41364c8f3d4c52e753173f0f",
 "card_nc": false
}