{"url":"/dataset/dialfact","name":"DialFact","full_name":null,"description_markdown":"DialFact is a testing benchmark dataset of 22,245 annotated conversational claims, paired with pieces of evidence from Wikipedia. There are three sub-tasks in DialFact: 1) Verifiable claim detection task distinguishes whether a response carries verifiable factual information; 2) Evidence retrieval task retrieves the most relevant Wikipedia snippets as evidence; 3) Claim verification task predicts a dialogue response to be supported, refuted, or not enough information.\r\n\r\nDescription from: [DialFact: A Benchmark for Fact-Checking in Dialogue](https://arxiv.org/abs/2110.08222)","description_withheld":null,"homepage":"https://arxiv.org/pdf/2110.08222.pdf","introduced_date":"2021-10-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/dialfact-a-benchmark-for-fact-checking-in","title":"DialFact: A Benchmark for Fact-Checking in Dialogue","first_author":"Prakhar Gupta","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["DialFact"],"data_loaders":[],"num_papers_in_archive":13,"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."}