{"url":"/dataset/rpeval","name":"RPEval","full_name":"Role-Playing Evaluation Dataset","description_markdown":"Role-Playing Eval (RPEval) is a benchmark dataset designed to evaluate large language models' role-playing abilities across emotional understanding, decision-making, moral alignment, and in-character consistency.","description_withheld":null,"homepage":"https://github.com/yelboudouri/RPEval","introduced_date":"2025-05-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/role-playing-evaluation-for-large-language","title":"Role-Playing Evaluation for Large Language Models","first_author":"Yassine El Boudouri","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RPEval"],"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."}