datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
xstory_cloze
Dataset Card for XStoryCloze
Dataset Summary
XStoryCloze consists of the professionally translated version of the English StoryCloze dataset (Spring 2016 version) to 10 non-English languages. This dataset is released by Meta AI.
Supported Tasks and Leaderboards
commonsense reasoning
Languages
en, ru, zh (Simplified), es (Latin America), ar, hi, id, te, sw, eu, my.
Dataset Structure
Data Instances
Size of downloaded dataset… See the full description on the dataset page: https://huggingface.co/datasets/juletxara/xstory_cloze.story_clozestory_cloze-2016
Dataset Card for "story_cloze-2016"
More Information needed
Note: This dataset was utilized for the evaluation of probability-based prompt selection techniques in the paper 'Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis'. It differs from the actual benchmark dataset.
story_clozewmdp_bio_robust_clozeOmni-Cloze
Omni-Cloze Benchmark
📖 Paper | 🕵️ Omni-Detective Pipeline | 🧑🏫 Omni-Cloze Benchmark
Guides
Omni-Cloze frames detailed captioning evaluation as a cloze-style multiple-choice proxy task. Omni-Cloze is a unified benchmark for evaluating detailed captioning across audio-only, visual-only, and audio–visual settings. The dataset spans 9 main domains and 47 sub-categories covering diverse topics such as education, entertainment, sports, news, science, and lifestyle, with a… See the full description on the dataset page: https://huggingface.co/datasets/BoJack/Omni-Cloze.wmdp_bio_clozewino_bias_cloze1code_x_glue_cc_cloze_testing_all
Dataset Card for "code_x_glue_cc_cloze_testing_all"
Dataset Summary
CodeXGLUE ClozeTesting-all dataset, available at https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/ClozeTesting-all
Cloze tests are widely adopted in Natural Languages Processing to evaluate the performance of the trained language models. The task is aimed to predict the answers for the blank with the context of the blank, which can be formulated as a multi-choice classification problem.
Here we… See the full description on the dataset page: https://huggingface.co/datasets/google/code_x_glue_cc_cloze_testing_all.code_x_glue_cc_cloze_testing_maxmin
Dataset Card for "code_x_glue_cc_cloze_testing_maxmin"
Dataset Summary
CodeXGLUE ClozeTesting-maxmin dataset, available at https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/ClozeTesting-maxmin
Cloze tests are widely adopted in Natural Languages Processing to evaluate the performance of the trained language models. The task is aimed to predict the answers for the blank with the context of the blank, which can be formulated as a multi-choice classification problem.… See the full description on the dataset page: https://huggingface.co/datasets/google/code_x_glue_cc_cloze_testing_maxmin.story_clozerocstories-cloze
ROCStories & Story Cloze Test Dataset
This dataset contains the ROCStories corpus and the Story Cloze Test evaluation sets, originally released by the Story Cloze Test team at the University of Rochester.
story_cloze_pt
Dataset Card for "story_cloze_pt"
This is a portuguese translation of the xstory_cloze dataset. The translation was performed using the Google Translate API.
This dataset follows the same structure as the original.
lmeh-story-cloze-2016
Dataset Card for "lmeh-story-cloze-2016"
More Information needed
wino_bias_cloze2task105_story_cloze-rocstories_sentence_generation
Dataset Card for Natural Instructions (https://github.com/allenai/natural-instructions) Task: task105_story_cloze-rocstories_sentence_generation
Additional Information
Citation Information
The following paper introduces the corpus in detail. If you use the corpus in published work, please cite it:
@misc{wang2022supernaturalinstructionsgeneralizationdeclarativeinstructions,
title={Super-NaturalInstructions: Generalization via Declarative Instructions on… See the full description on the dataset page: https://huggingface.co/datasets/Lots-of-LoRAs/task105_story_cloze-rocstories_sentence_generation.xstory-cloze-ftp
XStoryCloze-FTP
A first-token-prediction (FTP) reframing of juletxara/xstory_cloze.
Each example is a single text sequence ending in Answer： (fullwidth U+FF1A, no trailing space) so a model can predict the answer as one token. Format matches lm-evaluation-harness's MCQA template byte-for-byte.
Format
Example (en):
<sentence 1>
<sentence 2>
<sentence 3>
<sentence 4>
A: <ending 1>
B: <ending 2>
Answer：
Schema: question_id: int, text: str, answer_label: str (one of… See the full description on the dataset page: https://huggingface.co/datasets/mikaberidze/xstory-cloze-ftp.yue_xstory_cloze
Dataset Card for Cantonese XStoryCloze
This dataset is a Cantonese translation of the Simplified Chinese subset of juletxara/xstory_cloze. For more detailed information about the original dataset, please refer to the provided link.
This dataset is translated by indiejoseph/bart-translation-zh-yue and has not undergone any manual verification. The content may be inaccurate or misleading. please keep this in mind when using this dataset.
Sample
{
"input_sentence_1":… See the full description on the dataset page: https://huggingface.co/datasets/hon9kon9ize/yue_xstory_cloze.crows_pairs_clozeA subset of Crows-Pairs (total 1340). Dropped instances where sentence pairs differ by more than one word.
Normalization fixes: - Punctuation correction (periods, commas) - Capitalization - Typos - Whitespace cleanup - Hyphenation standardization to support cloze pairs
Source: https://gitlab.inria.fr/french-crows-pairs/acl-2022-paper-data-and-code
@inproceedings{neveol-etal-2022-french,
title = "{F}rench {C}row{S}-Pairs: Extending a challenge dataset for measuring social bias in… See the full description on the dataset page: https://huggingface.co/datasets/elidek-themis/crows_pairs_cloze.morphbench-verb-cloze
MorphBench — contextual verb-inflection cloze (EN / DE / FR)
A verb in a natural sentence is replaced by the marker [x]. The prompt
gives the lemma and a partial feature bundle; the sentence supplies
exactly the missing dimension. The model generates the surface form.
prompt : cloze lemma=<L> context=<sentence with [x]> feats=<partial feats> ->
gold : the inflected surface form
The benchmark exists to test whether a morphology-aware tokenizer helps a
small LM inflect words it… See the full description on the dataset page: https://huggingface.co/datasets/yuanxin112/morphbench-verb-cloze.javanese_sundanese_story_clozeCloze-SSH
SSH Cloze Benchmark
A Cloze-style benchmark for evaluating language models on Social Sciences and Humanities (SSH) text understanding. The benchmark measures whether a model can choose between two equivalent candidate tokens (e.g. higher vs. lower, positive vs. negative) in the context of an academic abstract, where the correct choice requires domain knowledge rather than general English fluency.
This dataset was introduced in the technical report SHARE: Social-Humanities AI for… See the full description on the dataset page: https://huggingface.co/datasets/Joaoffg/Cloze-SSH.Cloze_QA_Dataset_Wikitext2
Cloze QA Dataset (WikiText-2)
Dataset Description
The Cloze QA Dataset is automatically generated from the WikiText-2 corpus. It contains fill-in-the-blank (cloze) style questions derived directly from sentences in Wikipedia articles. This dataset is particularly useful for evaluating local recall, reading comprehension, and contextual understanding.
Each document produces exactly three unique QA pairs, preserving document structure and sentence alignment while… See the full description on the dataset page: https://huggingface.co/datasets/CGU-Widelab/Cloze_QA_Dataset_Wikitext2.mmlu_auxiliary_train_formatted_clozehukukbert-cloze-benchmark
Turkish Legal Cloze Benchmark (JSONL)
A small-scale Cloze-style multiple-choice benchmark for evaluating Turkish legal-domain language models.
The dataset is designed to test whether models understand legal terminology, doctrinal structure, and domain-specific phrasing in Turkish law.
Dataset Format
Each example is stored as one JSON object per line (JSONL).
Schema
{
"id": "string",
"sentence": "string with [MASK] placeholder",
"options": ["choice1"… See the full description on the dataset page: https://huggingface.co/datasets/turkhukuk/hukukbert-cloze-benchmark.historical-clozewino_bias_clozemmlu_auxiliary_train_formatted_cloze_20250619-1406historical-cloze-max-filteredmmlu_auxiliary_train_formatted_cloze_20250619-1417