{"url":"/dataset/off-topic","name":"Off-Topic","full_name":null,"description_markdown":"This dataset consists of synthetic LLM system prompts paired with user prompts, classified as either off-topic or on-topic. The aim is to provide realistic, real-world-inspired examples reflecting how large language models (LLMs) are used today for both open-ended and closed-ended tasks, such as text generation and classification. This dataset can be used for training and benchmarking off-topic guardrails.","description_withheld":null,"homepage":"","introduced_date":"2024-11-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-flexible-large-language-models-guardrail","title":"A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection","first_author":"Gabriel Chua","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Off-Topic"],"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."}