{
 "id": "LequeuISIR/GDN-CC",
 "owner": "LequeuISIR",
 "name": "GDN-CC",
 "downloads": 163,
 "likes": 4,
 "last_modified": "2026-09-14T12:01:30.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "Grand Débat National",
   "licence": null,
   "found": false,
   "evidence": null
  }
 ],
 "gated": false,
 "tasks": [
  "text-classification",
  "text-generation"
 ],
 "citation": "@inproceedings{lequeu-etal-2026-gdn,\n    title = \"The {GDN}-{CC} Dataset: Automatic Corpus Clarification for {AI}-enhanced Democratic Citizen Consultations\",\n    author = {Lequeu, Pierre-Antoine  and\n      Labat, L{\\'e}o  and\n      Cave, Laur{\\`e}ne  and\n      Lejeune, Ga{\\\"e}l  and\n      Yvon, Fran{\\c{c}}ois  and\n      Piwowarski, Benjamin},\n    editor = \"Liakata, Maria  and\n      Moreira, Viviane P.  and\n      Zhang, Jiajun  and\n      Jurgens, David\",\n    booktitle = \"Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2026\",\n    address = \"San Diego, California, United States\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.acl-long.1523/\",\n    doi = \"10.18653/v1/2026.acl-long.1523\",\n    pages = \"32976--33006\",\n    ISBN = \"979-8-89176-390-6\",\n    abstract = \"LLMs are ubiquitous in modern NLP, and while their applicability extends to texts produced for democratic activities such as online deliberations or large-scale citizen consultations, ethical questions have been raised for their usage as analysis tools. We continue this line of research with two main goals: (a) to develop resources that can help standardize citizen contributions in public forums at the \\textbf{pragmatic level}, and make them easier to use in topic modeling and political analysis; (b) to study how well this standardization can reliably be performed by sm",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID for at least one declared source dataset.",
 "revision": "fa815a895f31204102fb706a73829264ad22f3ab",
 "stated_evidence": "https://huggingface.co/datasets/LequeuISIR/GDN-CC/blob/fa815a895f31204102fb706a73829264ad22f3ab/README.md",
 "file_evidence": "https://huggingface.co/datasets/LequeuISIR/GDN-CC/tree/fa815a895f31204102fb706a73829264ad22f3ab",
 "card_nc": false
}