{"url":"/dataset/hixstest","name":"HiXSTest","full_name":"Hindi XSTest","description_markdown":"For testing refusal behavior in a language-specific setting, we introduce HiXSTest — a set of manually curated prompts in the Hindi language designed to measure exaggerated safety. It comprises 25 safe-unsafe pairs of prompts, carefully phrased to challenge the LLMs’ safety boundaries.","description_withheld":null,"homepage":"https://huggingface.co/datasets/walledai/HiXSTest","introduced_date":"2024-08-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/walledeval-a-comprehensive-safety-evaluation","title":"WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models","first_author":"Prannaya Gupta","url":null},"license":{"name":"Apache 2.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"},{"name":"AI and Safety","url":"/task/ai-and-safety","datasets_with_task":"/datasets/task/ai-and-safety"}],"languages":[{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["HiXSTest"],"data_loaders":[],"num_papers_in_archive":1,"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."}