{
 "id": "mks-logic/SPY",
 "owner": "mks-logic",
 "name": "SPY",
 "downloads": 566,
 "likes": 6,
 "last_modified": "2025-04-29T21:35:31.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "token-classification"
 ],
 "citation": "@inproceedings{savkin-etal-2025-spy,\n    title = \"{SPY}: Enhancing Privacy with Synthetic {PII} Detection Dataset\",\n    author = \"Maksim Savkin, Timur Ionov and Vasily Konovalov\",\n    editor = \"Abteen Ebrahimi, Samar Haider, Emmy Liu, Sammar Haider, Maria Leonor Pacheco and Shira Wein\",\n    booktitle = \"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)\",\n    month = apr,\n    year = \"2025\",\n    address = \"Albuquerque, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.naacl-srw.23/\",\n    pages = \"236--246\",\n    ISBN = \"979-8-89176-192-6\",\n    abstract = \"We introduce **SPY Dataset**: a novel synthetic dataset for the task of **Personal Identifiable Information (PII) detection**, underscoring the significance of protecting PII in modern data processing. Our research innovates by leveraging Large Language Models (LLMs) to generate a dataset that emulates real-world PII scenarios. Through evaluation, we validate the dataset`s quality, providing a benchmark for PII detection. Comparative analyses reveal that while PII and Named Entity Recognition (NER) share similarities, **dedicated NER models exhibit limitations** when applied to PII-specific contexts. This work contributes to the field by making the generation methodology and the generated dataset publicly, thereby enabling further re",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "093be5a0235c9e15bc1c364f10ac48b9563de34c",
 "stated_evidence": "https://huggingface.co/datasets/mks-logic/SPY/blob/093be5a0235c9e15bc1c364f10ac48b9563de34c/README.md",
 "file_evidence": "https://huggingface.co/datasets/mks-logic/SPY/tree/093be5a0235c9e15bc1c364f10ac48b9563de34c",
 "card_nc": false
}