{"url":"/dataset/stereoset","name":"StereoSet","full_name":null,"description_markdown":"A large-scale natural dataset in English to measure stereotypical biases in four domains: gender, profession, race, and religion.\r\n\r\nSource: [StereoSet: Measuring stereotypical bias in pretrained language models](/paper/stereoset-measuring-stereotypical-bias-in)","description_withheld":null,"homepage":"https://github.com/moinnadeem/stereoset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/stereoset-measuring-stereotypical-bias-in","title":"StereoSet: Measuring stereotypical bias in pretrained language models","first_author":"Moin Nadeem","url":null},"license":{"name":"CC-BY-SA-4.0","url":"https://github.com/moinnadeem/StereoSet/blob/master/LICENSE.md"},"modalities":[],"tasks":[{"name":"Bias Detection","url":"/task/bias-detection","datasets_with_task":"/datasets/task/bias-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["StereoSet"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/McGill-NLP/stereoset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/stereoset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/moinnadeem/StereoSet","url":"https://github.com/moinnadeem/stereoset","frameworks":[]}],"num_papers_in_archive":156,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset_variant":"StereoSet","rows":11,"metrics":["ICAT Score","LMS","SS"],"first_row_in_archive_order":{"model":"GPT-2 (small)","paper":"/paper/stereoset-measuring-stereotypical-bias-in","metrics":{"ICAT Score":"72.97"},"code_links":[{"title":"moinnadeem/StereoSet","url":"https://github.com/moinnadeem/StereoSet"},{"title":"kanekomasahiro/evaluate_bias_in_mlm","url":"https://github.com/kanekomasahiro/evaluate_bias_in_mlm"},{"title":"zalkikar/mlm-bias","url":"https://github.com/zalkikar/mlm-bias"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stereoset-measuring-stereotypical-bias-in","title":"StereoSet: Measuring stereotypical bias in pretrained language models","date":"2020-04-20","rows_on_this_dataset":8,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}