{"url":"/dataset/do-not-answer","name":"Do-Not-Answer","full_name":null,"description_markdown":"**Do-Not-Answer** is a dataset to evaluate safeguards in large language models, and deploy safer open-source LLMs at a low cost. The dataset is curated and filtered to consist only of instructions that responsible language models should not follow. We annotate and assess the responses of six popular LLMs to these instructions.","description_withheld":null,"homepage":"https://github.com/Libr-AI/do-not-answer","introduced_date":"2023-08-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/do-not-answer-a-dataset-for-evaluating","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","first_author":"Yuxia Wang","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/Libr-AI/do-not-answer/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["Do-Not-Answer"],"data_loaders":[],"num_papers_in_archive":22,"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."}