CIIRC-NLP/truthful_qa-cs

---
language:
- cs
license: apache-2.0
size_categories:
- n<1K
task_categories:
- multiple-choice
- question-answering
pretty_name: Czech TruthfulQA
dataset_info:
- config_name: multiple_choice
features:
- name: question
dtype: string
- name: mc1_targets
struct:
- name: choices
sequence: string
- name: labels
sequence: int32
- name: mc2_targets
struct:
- name: choices
sequence: string
- name: labels
sequence: int32
splits:
- name: validation
num_bytes: 650313
num_examples: 817
download_size: 312789
dataset_size: 650313
- config_name: shuffled_mc1
features:
- name: question
dtype: string
- name: choices
sequence: string
- name: target_idx
dtype: int64
splits:
- name: validation
num_bytes: 286901
num_examples: 817
download_size: 150893
dataset_size: 286901
configs:
- config_name: multiple_choice
data_files:
- split: validation
path: multiple_choice/validation-*
- config_name: shuffled_mc1
data_files:
- split: validation
path: shuffled_mc1/validation-*
---

# Czech TruthfulQA

This is a Czech translation of the original [TruthfulQA](https://huggingface.co/datasets/truthful_qa) dataset, created using the [WMT 21 En-X](https://huggingface.co/facebook/wmt21-dense-24-wide-en-x) model.
Only the multiple-choice variant of the dataset is included.

The translation was completed for use within the [Czech-Bench](https://gitlab.com/jirkoada/czech-bench) evaluation framework.
The script used for translation can be reviewed [here](https://gitlab.com/jirkoada/czech-bench/-/blob/main/benchmarks/dataset_translation.py?ref_type=heads).

## Citation

Original dataset:

```bibtex
@misc{lin2021truthfulqa,
title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
author={Stephanie Lin and Jacob Hilton and Owain Evans},
year={2021},
eprint={2109.07958},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```

Czech translation:

```bibtex
@masterthesis{jirkovsky-thesis,
author = {Jirkovský, Adam},
title = {Benchmarking Techniques for Evaluation of Large Language Models},
school = {Czech Technical University in Prague, Faculty of Electrical Engineering},
year = 2024,
URL = {https://dspace.cvut.cz/handle/10467/115227}
}
```

原始信息汇总

数据集概述

基本信息

• 数据集名称: Czech TruthfulQA
• 配置名称: multiple_choice
• 任务类别:
  • multiple-choice
  • question-answering
• 语言: cs
• 大小类别: n<1K
• 许可证: apache-2.0

数据结构

• 特征:
  • question: 字符串类型
  • mc1_targets:
    • choices: 字符串序列
    • labels: 整数序列
  • mc2_targets:
    • choices: 字符串序列
    • labels: 整数序列

数据集分割

• 验证集:
  • 大小: 650313字节
  • 示例数量: 817

下载信息

• 下载大小: 312789字节
• 数据集大小: 650313字节