{"url":"/dataset/truthgen","name":"TruthGen","full_name":null,"description_markdown":"TruthGen is a dataset of generated true and false statements, intended for research on truthfulness in reward models and language models, specifically in contexts where political bias is undesirable. This dataset contains 1,987 statement pairs (3,974 statements in total), with each pair containing one objectively true statement and one false statement. It spans a variety of everyday and scientific facts, excluding politically charged topics to the greatest extent possible. The dataset is particularly useful for evaluating reward models trained for alignment with truth, as well as for research on mitigating political bias while improving model accuracy on truth-related tasks.","description_withheld":null,"homepage":"https://huggingface.co/datasets/wwbrannon/TruthGen","introduced_date":"2024-09-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/on-the-relationship-between-truth-and","title":"On the Relationship between Truth and Political Bias in Language Models","first_author":"Suyash Fulay","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Reinforcement Learning","url":"/task/reinforcement-learning","datasets_with_task":"/datasets/task/reinforcement-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TruthGen"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wwbrannon/TruthGen","frameworks":["tf","pytorch","jax"]}],"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."}