{"url":"/dataset/summedits","name":"SummEdits","full_name":null,"description_markdown":"SummEdits is a benchmark designed to measure the ability of Large Language Models (LLMs) to reason about facts and detect inconsistencies. It was proposed as a new protocol for inconsistency detection benchmark creation.\r\n\r\nThe SummEdits benchmark is implemented across 10 domains. It is 20 times more cost-effective per sample than previous benchmarks and highly reproducible, with an estimated inter-annotator agreement of about 0.91.","description_withheld":null,"homepage":"https://github.com/salesforce/factualNLG","introduced_date":"2023-05-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/llms-as-factual-reasoners-insights-from","title":"LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond","first_author":"Philippe Laban","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["SummEdits"],"data_loaders":[],"num_papers_in_archive":5,"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":"2026-09-25T09:33:49+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."}