FiqhQA

# Dataset Card for Dataset Name

<!-- Provide a quick summary of the dataset. -->

Paper: Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions

## Dataset Details

### Dataset Description

<!-- Provide a longer summary of what this dataset is. -->

We introduce a novel benchmark FiqhQA focused on the LLM generated Islamic rulings explicitly categorized by
the four major Sunni schools of thought, in both Arabic and English.

- **Curated by:** [Farah Atif, Nursultan Askarbekuly, Kareem Darwish and Monojit Choudhury]
- **Language(s) (NLP):** [ARABIC, ENGLISH]

- **Paper Link :** https://arxiv.org/pdf/2508.08287

## Citation [optional]

<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

@misc{atif2025sacredsyntheticevaluatingllm,
title={Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions},
author={Farah Atif and Nursultan Askarbekuly and Kareem Darwish and Monojit Choudhury},
year={2025},
eprint={2508.08287},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2508.08287},
}

## Dataset Card Contact

[[e-mail]]

# 数据集卡片（Dataset Card）：FiqhQA

<!-- 提供数据集的快速概述 -->

关联论文：《宗教与合成？评估大语言模型（LLM）在宗教问题上的可靠性与弃权行为》（Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions）

## 数据集详情

### 数据集概述

本研究推出一款全新的基准数据集FiqhQA（伊斯兰教法问答数据集），该数据集收录由大语言模型（LLM）生成的伊斯兰教法裁决内容，并严格按照逊尼派四大主流教法学派进行分类，同时提供阿拉伯语与英语两种语言版本。

- **数据整理方**：[法拉赫·阿蒂夫、努尔苏丹·阿斯卡尔别科夫利、卡里姆·达维什、莫诺吉特·乔杜里]
- **自然语言处理（Natural Language Processing，NLP）所用语言**：[阿拉伯语、英语]

**论文链接**：https://arxiv.org/pdf/2508.08287

## 引用说明（可选）

<!-- 如果有介绍该数据集的论文或博客文章，请在此处添加其APA和BibTeX引用信息。 -->

**BibTeX引用格式**：

@misc{atif2025sacredsyntheticevaluatingllm,
title={Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions},
author={Farah Atif and Nursultan Askarbekuly and Kareem Darwish and Monojit Choudhury},
year={2025},
eprint={2508.08287},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2508.08287},
}

## 数据集卡片联系人

[[e-mail]]