{"url":"/dataset/cloth","name":"CLOTH","full_name":"CLOze test by TeacHers","description_markdown":"The Cloze Test by Teachers (**CLOTH**) benchmark is a collection of nearly 100,000 4-way multiple-choice cloze-style questions from middle- and high school-level English language exams, where the answer fills a blank in a given text. Each question is labeled with a type of deep reasoning it involves, where the four possible types are grammar, short-term reasoning, matching/paraphrasing, and long-term reasoning, i.e., reasoning over multiple sentences\n\nSource: [Recent Advances in Natural Language Inference:A Survey of Benchmarks, Resources, and Approaches](https://arxiv.org/abs/1904.01172)\nImage Source: [https://arxiv.org/pdf/1711.03225.pdf](https://arxiv.org/pdf/1711.03225.pdf)","description_withheld":null,"homepage":"https://www.cs.cmu.edu/~glai1/data/cloth/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-cloze-test-dataset-created-by","title":"Large-scale Cloze Test Dataset Created by Teachers","first_author":"Qizhe Xie","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CLOTH"],"data_loaders":[],"num_papers_in_archive":20,"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."}