{"url":"/dataset/havoc","name":"HAVOC","full_name":"Harmful Abstractions and Violations in Open Completions Benchmark","description_markdown":"measure the toxicity generated by language models across input severity and harm categories, by creating a new benchmark of open ended prefixes. We sampled 10,376 snippets from web pages across the dimensions and harms as described in the paper - https://arxiv.org/pdf/2505.02009.","description_withheld":null,"homepage":"https://github.com/themendu/TowardsSaferPretraining/blob/main/data/HAVOC","introduced_date":"2025-05-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/towards-safer-pretraining-analyzing-and","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","first_author":"Sai Krishna Mendu","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":"Misinformation","url":"/task/misinformation","datasets_with_task":"/datasets/task/misinformation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HAVOC"],"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."}