{"url":"/dataset/xstest","name":"XSTest","full_name":null,"description_markdown":"The XSTest dataset is a test suite designed to identify exaggerated safety behaviors in large language models. It was introduced to systematically study the phenomenon where some models refuse even clearly safe prompts if they use similar language to unsafe prompts or mention sensitive topics.","description_withheld":null,"homepage":"https://github.com/paul-rottger/exaggerated-safety","introduced_date":"2023-08-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/xstest-a-test-suite-for-identifying","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","first_author":"Paul Röttger","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["XSTest"],"data_loaders":[],"num_papers_in_archive":81,"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."}