{"url":"/dataset/cidar","name":"CIDAR","full_name":null,"description_markdown":"CIDAR contains 10,000 instructions and their output. The dataset was created by selecting around 9,109 samples from Alpagasus dataset then translating it to Arabic using ChatGPT. In addition, we append that with around 891 Arabic grammar instructions from the webiste Ask the teacher. All the 10,000 samples were reviewed by around 12 reviewers.","description_withheld":null,"homepage":"https://huggingface.co/datasets/arbml/CIDAR","introduced_date":"2024-02-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/cidar-culturally-relevant-instruction-dataset","title":"CIDAR: Culturally Relevant Instruction Dataset For Arabic","first_author":"Zaid Alyafeai","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/deed.en"},"modalities":[],"tasks":[{"name":"Instruction Following","url":"/task/instruction-following","datasets_with_task":"/datasets/task/instruction-following"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["CIDAR"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}