{"url":"/dataset/lm-email-address-leakage","name":"LM Email Address Leakage","full_name":null,"description_markdown":"Are Large Pre-Trained Language Models Leaking Your Personal Information? We analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with contexts of the email address or prompts containing the owner's name.","description_withheld":null,"homepage":"https://github.com/jeffhj/LM_PersonalInfoLeak","introduced_date":"2022-05-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/are-large-pre-trained-language-models-leaking","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","first_author":"Jie Huang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Memorization","url":"/task/memorization","datasets_with_task":"/datasets/task/memorization"}],"languages":[],"variants":["LM Email Address Leakage"],"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."}