{"url":"/dataset/sudoer","name":"SUDOER","full_name":"System/User Dataset for Obedience Evaluation in Responses","description_markdown":"The dataset aims to provide system prompts and user prompts for assistant. You should make random pairs and compute human preference for both system prompt obedience and user prompt relevance through A/B testing.","description_withheld":null,"homepage":"https://vermeille.github.io/cfg-llm/","introduced_date":"2023-06-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","first_author":"Guillaume Sanchez","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SUDOER"],"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."}