# Ta'keed: The First Generative Fact-Checking System for Arabic Claims

arXiv: https://arxiv.org/abs/2401.14067 · HTML: https://mlsanity.com/paper/2401.14067/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 9 of 9)

- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Fake News Detection on Social Media: A Data Mining Perspective](https://mlsanity.com/paper/1708.01967/) (2017)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [Tanbih: Get To Know What You Are Reading](https://mlsanity.com/paper/1910.02028/) (2019)
- [ArCOV19-Rumors: Arabic COVID-19 Twitter Dataset for Misinformation Detection](https://mlsanity.com/paper/2010.08768/) (2020)
- [a survey on GPT-3](https://mlsanity.com/paper/2212.00857/) (2022)
- [ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks](https://mlsanity.com/paper/2004.05861/) (2020)
- [Fake or Real? A Study of Arabic Satirical Fake News](https://mlsanity.com/paper/2011.00452/) (2020)

## Built on by (most cited first, 3 of 3)

- [Generative Large Language Models in Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2407.02351/) (2024)
- [A Generative-AI-Driven Claim Retrieval System Capable of Detecting and Retrieving Claims from Social Media Platforms in Multiple Languages](https://mlsanity.com/paper/2504.20668/) (2025)
- [ARAFA: An LLM-Generated Arabic Fact-Checking Dataset](https://mlsanity.com/paper/2609.25833/) (2026)

## Abstract (arXiv)

This paper introduces Ta'keed, an explainable Arabic automatic fact-checking system. While existing research often focuses on classifying claims as "True" or "False," there is a limited exploration of generating explanations for claim credibility, particularly in Arabic. Ta'keed addresses this gap by assessing claim truthfulness based on retrieved snippets, utilizing two main components: information retrieval and LLM-based claim verification. We compiled the ArFactEx, a testing gold-labelled dataset with manually justified references, to evaluate the system. The initial model achieved a promising F1 score of 0.72 in the classification task. Meanwhile, the system's generated explanations are compared with gold-standard explanations syntactically and semantically. The study recommends evaluating using semantic similarities, resulting in an average cosine similarity score of 0.76. Additionally, we explored the impact of varying snippet quantities on claim classification accuracy, revealing a potential correlation, with the model using the top seven hits outperforming others with an F1 score of 0.77.