{
 "id": "guneeshv/REDACT-PII-Benchmark",
 "owner": "guneeshv",
 "name": "REDACT-PII-Benchmark",
 "downloads": 138,
 "likes": 0,
 "last_modified": "2026-08-23T18:22:38.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "redact-dataset-terms",
 "licence_link": "https://github.com/guneeshvats/REDACT-PII-Benchmark/blob/main/DATASET_TERMS.md",
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "token-classification"
 ],
 "citation": "@inproceedings{vats2026redact,\n  title     = {REDACT: A Systematically Controlled Multilingual Benchmark for Personal Information Detection},\n  author    = {Guneesh Vats and Anubha Agrawal and Shikha Singhal and Ajita Dash and Praison Selvaraj and Vidhan Jhawar and Ranga Prasad Chenna and Bharadwaj Y M G},\n  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track},\n  year      = {2026},\n  note      = {To appear}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "1d7fef611cbaad42ba19666e7d7238ed45b264dd",
 "stated_evidence": "https://huggingface.co/datasets/guneeshv/REDACT-PII-Benchmark/blob/1d7fef611cbaad42ba19666e7d7238ed45b264dd/README.md",
 "file_evidence": "https://huggingface.co/datasets/guneeshv/REDACT-PII-Benchmark/blob/1d7fef611cbaad42ba19666e7d7238ed45b264dd/LICENSE",
 "card_nc": false
}