{"url":"/dataset/kmir","name":"KMIR","full_name":"Knowledge Memorization, Identification, and Reasoning","description_markdown":"**KMIR** (**Knowledge Memorization, Identification, and Reasoning**) is a benchmark that covers 3 types of knowledge, including general knowledge, domain-specific knowledge, and commonsense, and provides 184,348 well-designed questions. KMIR can be used for evaluating knowledge memorization, identification and reasoning abilities of language models.","description_withheld":null,"homepage":"https://github.com/KMIR2021/KMIR","introduced_date":"2022-02-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/kmir-a-benchmark-for-evaluating-knowledge","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","first_author":"Daniel Gao","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["KMIR"],"data_loaders":[],"num_papers_in_archive":3,"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."}