{"url":"/dataset/indonli","name":"IndoNLI","full_name":null,"description_markdown":"IndoNLI is the first human-elicited NLI dataset for Indonesian consisting of nearly 18K sentence pairs annotated by crowd workers and experts.","description_withheld":null,"homepage":"https://github.com/ir-nlp-csui/indonli","introduced_date":"2021-10-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/indonli-a-natural-language-inference-dataset","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","first_author":"Rahmad Mahendra","url":null},"license":{"name":"CC-BY-SA","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"}],"languages":[{"name":"Indonesian","url":"/datasets/language/indonesian"}],"variants":["IndoNLI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/afaji/indonli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/indonli","frameworks":["tf","pytorch","jax"]}],"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":"2026-09-24T18:15:14+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."}