# Large-scale Cloze Test Dataset Created by Teachers Source: [Large-scale Cloze Test Dataset Created by Teachers]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:09:58.940Z Authors: Qizhe Xie, Guokun Lai, Zihang Dai, Eduard Hovy Published: 2017-11-09T01:41:12.000Z ## Abstract Cloze tests are widely adopted in language exams to evaluate students' language proficiency. In this paper, we propose the first large-scale human-created cloze test dataset CLOTH, containing questions used in middle-school and high-school language exams. With missing blanks carefully created by teachers and candidate choices purposely designed to be nuanced, CLOTH requires a deeper language understanding and a wider attention span than previously automatically-generated cloze datasets. We test the performance of dedicatedly designed baseline models including a language model trained on the One Billion Word Corpus and show humans outperform them by a significant margin. We investigate the source of the performance gap, trace model deficiencies to some distinct properties of CLOTH, and identify the limited ability of comprehending the long-term context to be the key bottleneck. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multiple Choice Question Distractor Generation on CLOTH (test)](): Multiple Choice Question Distractor Generation; Cloth (test); Chosen Ratio: 83.2. - [Distractor Generation on CLOTH (test)](): Distractor Generation; Cloth (test); Invalid Ratio (Easy): not recorded. ## Original sources and implementation [Original paper]() [PDF]()