{"url":"/dataset/hans","name":"HANS","full_name":"Heuristic Analysis for NLI Systems","description_markdown":"The HANS (Heuristic Analysis for NLI Systems) dataset which contains many examples where the heuristics fail. \r\n\r\nSource: [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://arxiv.org/abs/1902.01007)","description_withheld":null,"homepage":"https://github.com/tommccoy1/hans","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"}],"languages":[],"variants":["HANS"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jhu-cogsci/hans","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hans","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tommccoy1/hans","url":"https://github.com/tommccoy1/hans","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-hans","task":"Natural Language Inference","dataset_variant":"HANS","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Roberta-large","paper":"/paper/generating-data-to-mitigate-spurious-1","metrics":{"1:1 Accuracy":"78.65"},"code_links":[{"title":"jimmycode/gen-debiased-nli","url":"https://github.com/jimmycode/gen-debiased-nli"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/generating-data-to-mitigate-spurious-1","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","date":"2022-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}