{"url":"/dataset/fib","name":"FIB","full_name":"Factual Inconsistency Benchmark","description_markdown":"Factual Inconsistency Benchmark (**FIB**) is a benchmark that focuses on the task of summarization. Specifically, the benchmark involves comparing the scores an LLM assigns to a factually consistent versus a factual inconsistent summary for an input news article. For factually consistent summaries, human-written reference summaries are used to manually verify as factually consistent.\r\n\r\nSource: [Evaluating the Factual Consistency of Large Language Models Through Summarization](https://arxiv.org/pdf/2211.08412v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.08412v1.pdf](https://arxiv.org/pdf/2211.08412v1.pdf)","description_withheld":null,"homepage":"https://github.com/r-three/fib","introduced_date":"2022-11-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/evaluating-the-factual-consistency-of-large","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization","first_author":"Derek Tam","url":null},"license":{"name":"CC BY 4.0 License","url":"https://github.com/r-three/fib/blob/master/dataset_LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"News Summarization","url":"/task/news-summarization","datasets_with_task":"/datasets/task/news-summarization"}],"languages":[],"variants":["FIB"],"data_loaders":[],"num_papers_in_archive":2,"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."}