{
 "id": "nlip/DIWALI",
 "owner": "nlip",
 "name": "DIWALI",
 "downloads": 55,
 "likes": 7,
 "last_modified": "2026-04-20T06:30:49.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{sahoo-etal-2025-diwali,\n    title = \"{DIWALI} - Diversity and Inclusivity a{W}are cu{L}ture specific Items for {I}ndia: Dataset and Assessment of {LLM}s for Cultural Text Adaptation in {I}ndian Context\",\n    author = \"Sahoo, Pramit  and\n      Brahma, Maharaj  and\n      Desarkar, Maunendra Sankar\",\n    editor = \"Christodoulopoulos, Christos  and\n      Chakraborty, Tanmoy  and\n      Rose, Carolyn  and\n      Peng, Violet\",\n    booktitle = \"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou, China\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.emnlp-main.1706/\",\n    doi = \"10.18653/v1/2025.emnlp-main.1706\",\n    pages = \"33599--33626\",\n    ISBN = \"979-8-89176-332-6\",\n    abstract = \"Large language models (LLMs) are widely used in various tasks and applications. However, despite their wide capabilities, they are shown to lack cultural alignment (Ryan et al., 2024; AlKhamissi et al., 2024) and produce biased generations (Naous et al., 2024) due to a lack of cultural knowledge and competence. Evaluation of LLMs for cultural awareness and alignment is particularly challenging due to the lack of proper evaluation metrics and unavailability of culturally grounded datasets representing the vast complexity of cultures at the regional and sub-regional levels. Existing datasets for culture specific items (CSIs) focus primaril",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "7ca0038ca597979faefe5b8735f11431acc6a4b9",
 "stated_evidence": "https://huggingface.co/datasets/nlip/DIWALI/blob/7ca0038ca597979faefe5b8735f11431acc6a4b9/README.md",
 "file_evidence": "https://huggingface.co/datasets/nlip/DIWALI/tree/7ca0038ca597979faefe5b8735f11431acc6a4b9",
 "card_nc": false
}