{"url":"/dataset/honest-en","name":"HONEST","full_name":"Hurtful Sentence Completion in English Language Models","description_markdown":"The HONEST dataset is a template-based corpus for testing the hurtfulness of sentence completions in language models (e.g., BERT) in six different languages (English, Italian, French, Portuguese, Romanian, and Spanish).  HONEST is composed of 420 instances for each language, which are generated from 28 identity terms (14 male and 14 female) and 15 templates. It uses a set of identifier terms in singular and plural (i.e., woman, women, girl, boys) and a series of predicates (i.e., “works as [MASK]”, “is known for [MASK]”). The objective is to use language models to fill the sentence, then the hurtfulness of the completion is evaluated.","description_withheld":null,"homepage":"https://github.com/MilaNLProc/honest","introduced_date":"2021-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","first_author":"Debora Nozza","url":null},"license":{"name":"MIT license","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Hurtful Sentence Completion","url":"/task/hurtful-sentence-completion","datasets_with_task":"/datasets/task/hurtful-sentence-completion"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HONEST"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MilaNLProc/honest","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/milanlproc/honest","url":"https://github.com/milanlproc/honest","frameworks":[]}],"num_papers_in_archive":25,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hurtful-sentence-completion-on-honest-en","task":"Hurtful Sentence Completion","dataset_variant":"HONEST","rows":5,"metrics":["HONEST"],"first_row_in_archive_order":{"model":"BERT-base","paper":"/paper/honest-measuring-hurtful-sentence-completion","metrics":{"HONEST":"1.19"},"code_links":[{"title":"milanlproc/honest","url":"https://github.com/milanlproc/honest"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/honest-measuring-hurtful-sentence-completion","title":"HONEST: Measuring Hurtful Sentence Completion in Language Models","date":"2021-06-01","rows_on_this_dataset":5,"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."}