---
title: "QIAS 2025 — paper by Bouchekif et al. (2025)"
description: "QIAS 2025, a shared task at ArabicNLP 2025 (co-located with EMNLP 2025), tests how well large… 40 references, cited by 29 papers here."
authors: ["Abdessalam Bouchekif", "Samer Rashwani", "Emad Soliman Ali Mohamed", "Mutaz Alkhatib", "Heba Sbahi", "Shahd Gaben", "Wajdi Zaghouani", "Aiman Erbad", "Mohammed Ghaly"]
year: 2025
venue: "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks"
source: "https://aclanthology.org/2025.arabicnlp-sharedtasks.117/"
doi: "10.18653/v1/2025.arabicnlp-sharedtasks.117"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/bouchekif-2025-qias-2025-overview-shared-task/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/bouchekif-2025-qias-2025-overview-shared-task/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / QIAS 2025: Overview of the Shared Task on Islamic Inheritance Reasoning and Knowledge Assessment

# QIAS 2025: Overview of the Shared Task on Islamic Inheritance Reasoning and Knowledge Assessment

**Authors:** [Abdessalam Bouchekif](https://md.research.elamur.ai/free/en/authors/abdessalam-bouchekif/), [Samer Rashwani](https://md.research.elamur.ai/free/en/authors/samer-rashwani/), [Emad Soliman Ali Mohamed](https://md.research.elamur.ai/free/en/authors/emad-mohamed/), Mutaz Alkhatib, [Heba Sbahi](https://md.research.elamur.ai/free/en/authors/heba-sbahi/), [Shahd Gaben](https://md.research.elamur.ai/free/en/authors/shahd-gaben/), [Wajdi Zaghouani](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/), Aiman Erbad and [Mohammed Ghaly](https://md.research.elamur.ai/free/en/authors/mohammed-ghaly/) · **Year:** 2025 · **Venue:** [Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2025](https://md.research.elamur.ai/free/en/venues/arabicnlp/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.arabicnlp-sharedtasks.117/) · [PDF](https://aclanthology.org/2025.arabicnlp-sharedtasks.117.pdf) · [DOI 10.18653/v1/2025.arabicnlp-sharedtasks.117](https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.117) · [OpenAlex](https://openalex.org/W4416037597)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [29](https://md.research.elamur.ai/free/en/papers/bouchekif-2025-qias-2025-overview-shared-task/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
QIAS 2025, a shared task at ArabicNLP 2025 (co-located with EMNLP 2025), tests how well large language models handle Islamic legal reasoning and religious knowledge. It has two multiple-choice subtasks, each stratified by difficulty.

- **Subtask 1** covers inheritance law (ʿilm al-mawārīth). Systems must identify heirs, apply exclusion (ḥajb), and compute fractional shares, including the radd and ʿawl adjustments.
- **Subtask 2** covers broader Islamic disciplines such as fiqh, uṣūl al-fiqh, hadith sciences, Quranic studies and sīrah.

The inheritance data combines two sources. One part was produced from IslamWeb fatwas with Gemini 2.5 Pro and then checked by experts. The other part was produced from cases solved by the Almwareeth calculator. Participating systems relied mostly on chain-of-thought prompting, retrieval-augmented generation, ensembles and LoRA fine-tuning. Commercial models clearly outperformed open-source ones, and inheritance reasoning stayed harder than knowledge questions.

The organizers plan a follow-up edition in which systems solve inheritance cases end to end rather than choosing among options. They also want to encourage small open models. The task provides an expert-curated benchmark for a domain where precision matters and where models often produce confident errors.

## Key points
- **Participation:** 44 teams joined the development phase and 18 reached the test phase. Of these, 6 entered both subtasks, 8 only Task 1 and 2 only Task 2. Sixteen teams wrote system papers.
- **Task 1 data:**
  - 22,000 MCQs in total.
  - 10,446 come from IslamWeb fatwas, converted by Gemini 2.5 Pro and reviewed by four experts.
  - 11,554 were built with the Almwareeth calculator.
  - Questions are split into Beginner and Advanced levels.
  - A supplementary pool of 3,165 fatwas was also released.
- **Task 2 data:** questions have three difficulty levels (Beginner, Intermediate, Advanced).
- **Selected results:**
  - Athar's hybrid BM25 + dense retrieval with GPT reranking reached 92.7% on Subtask 2.
  - N&N's ensemble reached 89.9% on Subtask 2.
  - With chain-of-thought prompting, ANLPers raised Claude 3.7 Sonnet on inheritance from 67.0% to 81.0%.
  - ALLaM-7B scored 42.9% zero-shot.
- **Prior work:** reasoning models such as o3 (93.4%) and Gemini 2.5 (90.6%) far outperform Jais, Mistral and LLaMA, which all stay below 50%.

## Interesting ideas
- About half the inheritance questions were labelled by an algorithmic calculator rather than by people, so the gold answers come from a correct-by-construction solver.
- Answer options were cleaned so that numerically equivalent choices (such as 1/2 and 2/4) never appear together, which removes ambiguity about which option is correct.
- N&N had several LLMs vote and fell back to retrieval-augmented re-prompting only when they disagreed, so the expensive step runs only on contested items.
- Some teams forced outputs into the valid label set, either through constrained decoding over A–F or by regex extraction of the answer. This prevents free-form generations that cannot be scored.
- Errors were analysed by named reasoning phenomenon (ʿawl, ḥajb, tasheeh normalization) rather than only by overall accuracy, which shows exactly which rule step breaks.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): Mova's own symbolic solvers could generate maths word problems with guaranteed answers, providing gold training and evaluation data without manual annotation.
- **I2** (world): before comparing quantities or options, measures and fractions should be reduced to a canonical form so that equivalent values always match.
- **I3** (learn): when the witness parsers disagree on a silver tree, Mova could escalate to a higher LLM teacher tier, keeping costs low on sentences where they agree.
- **I4** (answer): Mova's test readers should map their final output onto the allowed answer space explicitly, and log a failure rather than guessing when no valid option is produced.
- **I5** (learn): Mova's evaluations could tag each failure with the pipeline step or rule it involves, such as unit conversion or event ordering, to guide self-induced repair rules.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Hamad bin Khalifa University](https://md.research.elamur.ai/free/en/universities/hamad-bin-khalifa-university/) — University, Doha, Qatar · 141 works · 14,175 citations
- [Qatar University](https://md.research.elamur.ai/free/en/universities/qatar-university/) — University, Doha, Qatar · 48 works · 1,026 citations
- [Northwestern University in Qatar](https://md.research.elamur.ai/free/en/universities/northwestern-university-in-qatar/) — University, Doha, Qatar · 24 works · 148 citations
- [Nazarbayev University](https://md.research.elamur.ai/free/en/universities/nazarbayev-university/) — University, Astana, Kazakhstan · 4 works · 44 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 182 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works

## Cite

Cite as: Abdessalam Bouchekif, Samer Rashwani, Emad Soliman Ali Mohamed, Mutaz Alkhatib, Heba Sbahi, Shahd Gaben, Wajdi Zaghouani, Aiman Erbad and Mohammed Ghaly. 2025. QIAS 2025: Overview of the Shared Task on Islamic Inheritance Reasoning and Knowledge Assessment. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{bouchekif2025qias,
  title = {{QIAS 2025: Overview of the Shared Task on Islamic Inheritance Reasoning and Knowledge Assessment}},
  author = {Abdessalam Bouchekif, Samer Rashwani, Emad Soliman Ali Mohamed, Mutaz Alkhatib, Heba Sbahi, Shahd Gaben, Wajdi Zaghouani, Aiman Erbad and Mohammed Ghaly},
  booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
  year = {2025},
  doi = {10.18653/v1/2025.arabicnlp-sharedtasks.117},
  url = {https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.117}
}
```

- [← previous OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure](https://md.research.elamur.ai/free/en/papers/wang-2025-opt-tree-speculative-decoding-adaptive/)
- [next → The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input](https://md.research.elamur.ai/free/en/papers/jacovi-2025-facts-grounding-leaderboard-benchmarking-llms/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

40 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ummar Abbas, Mohammad Shahmeer Ahmad, Firoj Alam, Enes Altinisik, Ehsannedin Asgari, Yazan Boshmaf, Sabri Boughorbel, Sanjay Chawla, Sham mur A. Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed K. Elma garmid, Mohamed Y. Eltabakh, Masoomali Fatehkia, Anastasios Fragkopoulos, Maram Hasanain, Majd Hawasly, and 22 others. 2025. [Fanar: An arabic centric multimodal generative AI platform](https://md.research.elamur.ai/free/en/papers/abbas-2025-fanar-arabic-centric-multimodal-generative/). arXiv preprint, arXiv:2501.13944. [↗](https://arxiv.org/abs/2501.13944)
2. Muhammad Abu Ahmad, Mohamad Ballout, Raia Abu Ahmad, and Elia Bruni. 2025. Transformer tafsir at qias 2025 shared task: Hybrid retrievalaugmented generation for islamic knowledge question answer ing. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Lin guistics. [find](https://scholar.google.com/scholar?q=Muhammad+Abu+Ahmad%2C+Mohamad+Ballout%2C+Raia+Abu+Ahmad%2C+and+Elia+Bruni%2E+2025%2E+Transformer+tafsir+at+qias+2025+shared+task%3A+Hybrid+retrievalaugmented+generation+for+islamic+knowledge+question+answer+ing%2E+)
3. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774. [↗](https://arxiv.org/abs/2303.08774)
4. Alaa N Akkila and Samy S Abu Naser. 2016. Proposed expert system for calculating inheritance in islam. International Journal of Advanced Research in Com puter Science. [find](https://scholar.google.com/scholar?q=Alaa+N+Akkila+and+Samy+S+Abu+Naser%2E+2016%2E+Proposed+expert+system+for+calculating+inheritance+in+islam%2E+International+Journal+of+Advanced+Research+in+Com+puter+Science%2E)
5. Mohammad ALSmadi. 2025. Qunlp at qias 2025 shared task: A twophase llm finetuning and retrievalaugmented generation approach for islamic inheritance reasoning. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mohammad+ALSmadi%2E+2025%2E+Qunlp+at+qias+2025+shared+task%3A+A+twophase+llm+finetuning+and+retrievalaugmented+generation+approach+for+islamic+inheritance+reasoning%2E+In+Proceedings+of+The+Third+Arabic+Natur)
6. Ahmet Yusuf Alan, Enis Karaarslan, and Ömer Ay din. 2024. A ragbased question answering system proposal for understanding islam: Mufassirqas llm. arXiv preprint arXiv:2401.15378. [↗](https://arxiv.org/abs/2401.15378)
7. Nourah Alangari and Nouf AlShenaifi. 2025. N&n at qias 2025: Chainofthought ensembles with retrievalaugmented framework for classical arabic islamic. In Proceedings of The Third Arabic Nat ural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Nourah+Alangari+and+Nouf+AlShenaifi%2E+2025%2E+N%26n+at+qias+2025%3A+Chainofthought+ensembles+with+retrievalaugmented+framework+for+classical+arabic+islamic%2E+In+Proceedings+of+The+Third+Arabic+Nat+ural+Langua)
8. Nouar AlDahoul and Yasir Zaki. 2025. [Nyuad at qias shared task: Benchmarking the legal reasoning of llms in arabic islamic inheritance cases](https://md.research.elamur.ai/free/en/papers/aldahoul-2025-nyuad-qias-shared-task-benchmarking/). In Proceed ings of The Third Arabic Natural Language Process ing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics.
9. Hayfa A Aleid and Aqil M Azmi. 2025. Hajjfqa: A benchmark arabic dataset for developing question answering systems on hajj fatwas: H. aleid and a. azmi. Journal of King Saud University Computer and Information Sciences, 37(6):135. [find](https://scholar.google.com/scholar?q=Hayfa+A+Aleid+and+Aqil+M+Azmi%2E+2025%2E+Hajjfqa%3A+A+benchmark+arabic+dataset+for+developing+question+answering+systems+on+hajj+fatwas%3A+H%2E+aleid+and+a%2E+azmi%2E+Journal+of+King+Saud+University+Computer+and+In)
10. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Al shamsi, Alessandro Cappelli, Ruxandra Cojocaru, Mérouane Debbah, Étienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, and 1 others. 2023. [The falcon series of open language models](https://md.research.elamur.ai/free/en/papers/almazrouei-2023-falcon-series-open-language-models/). arXiv preprint arXiv:2311.16867. [↗](https://arxiv.org/abs/2311.16867)
11. Sarah Alnefaie, Eric Atwell, and Mohammad Ammar Alsalka. 2023. Is gpt4 a good islamic expert for an swering quran questions? In Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023), pages 124–133. [find](https://scholar.google.com/scholar?q=Sarah+Alnefaie%2C+Eric+Atwell%2C+and+Mohammad+Ammar+Alsalka%2E+2023%2E+Is+gpt4+a+good+islamic+expert+for+an+swering+quran+questions%3F+In+Proceedings+of+the+35th+Conference+on+Computational+Linguistics+and+Spee)
12. Sanaa Alowaidi, Eric Atwell, and Mohammed Ammar Alsalka. 2025. Seateam at qias 2025: Enhancing llms for question answering in islamic texts. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sanaa+Alowaidi%2C+Eric+Atwell%2C+and+Mohammed+Ammar+Alsalka%2E+2025%2E+Seateam+at+qias+2025%3A+Enhancing+llms+for+question+answering+in+islamic+texts%2E+In+Proceedings+of+The+Third+Arabic+Natural+Language+Process)
13. Deepseekr1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948. — [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/) [↗](https://arxiv.org/abs/2501.12948)
14. Mohamed Motasim Hamed, Nada Ghneim, and Riad Sonbol. 2025. Hiast at qias 2025: Retrieval augmented llms with tophit web evidence for ara bic islamic reasoning qa. In Proceedings of The Third Arabic Natural Language Processing Confer ence (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mohamed+Motasim+Hamed%2C+Nada+Ghneim%2C+and+Riad+Sonbol%2E+2025%2E+Hiast+at+qias+2025%3A+Retrieval+augmented+llms+with+tophit+web+evidence+for+ara+bic+islamic+reasoning+qa%2E+In+Proceedings+of+The+Third+Arabic+Na)
15. Shatha Altammami. 2025. [Sha at the qias shared task: Llms for arabic islamic inheritance reasoning](https://md.research.elamur.ai/free/en/papers/altammami-2025-sha-qias-shared-task-llms/). In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [↗](https://doi.org/10.48448/2shm-0p85)
16. M. Saiful Bari, Yazeed Alnumay, Norah A. Alzahrani, Nouf M. Alotaibi, Hisham A. Alyahya, Sultan Al rashed, Faisal Mirza, Shaykhah Alsubaie, Hassan A. Alahmed, Ghadah Alabduljabbar, Raghad Alkhathran, Yousef Almushayqih, Raneem Alnajim, Salman Al subaihi, Maryam Al Mansour, Majed Alrubaian, Ali Alammari, Zaki Alawami, Abdulmohsen Al Thubaity, and 6 others. 2024. [Allam: Large lan guage models for arabic and english](https://md.research.elamur.ai/free/en/papers/bari-2024-allam-large-language-models-arabic/). arXiv preprint arXiv:2407.15390. [↗](https://arxiv.org/abs/2407.15390)
17. Salah Eddine Bekhouche, Abdellah Zakaria Sellam, Hichem Telli, Cosimo Distante, and Abdenour Hadid. 2025. Cvpd at qias 2025 shared task: An efficient encoderbased approach for islamic inheritance rea soning. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Lin guistics. [find](https://scholar.google.com/scholar?q=Salah+Eddine+Bekhouche%2C+Abdellah+Zakaria+Sellam%2C+Hichem+Telli%2C+Cosimo+Distante%2C+and+Abdenour+Hadid%2E+2025%2E+Cvpd+at+qias+2025+shared+task%3A+An+efficient+encoderbased+approach+for+islamic+inheritance+rea+)
18. Abdessalam Bouchekif, Samer Rashwani, Heba Sbahi, Shahd Gaben, Mutaz AlKhatib, and Mohammed Ghaly. 2025. Assessing large language models on is lamic legal reasoning: Evidence from inheritance law evaluation. In Proceedings of The Third Arabic Nat ural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Abdessalam+Bouchekif%2C+Samer+Rashwani%2C+Heba+Sbahi%2C+Shahd+Gaben%2C+Mutaz+AlKhatib%2C+and+Mohammed+Ghaly%2E+2025%2E+Assessing+large+language+models+on+is+lamic+legal+reasoning%3A+Evidence+from+inheritance+law+eval)
19. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Mar cel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobs son, Idan Szpektor, NanJiang Jiang, and 43 others. 2025. [Gemini 2.5: Pushing the Frontier with Ad vanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). arXiv preprint arXiv:2507.06261. Rapport technique, Équipe Gem ini, Google. [↗](https://arxiv.org/abs/2507.06261)
20. Eman Elrefai, Abdelrahman Ahmad, Aml Hassan Es mail, and Mohamed Lotfy Elrefai. 2025. [Gumball at qias 2025: Arabic llm automated reasoning in islamic inheritance](https://md.research.elamur.ai/free/en/papers/elrefai-2025-gumball-qias-2025-arabic-llm/). In Proceedings of The Third Arabic Nat ural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics.
21. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shi rong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Ruoyu+Zhang%2C+Runxin+Xu%2C+Qihao+Zhu%2C+Shi+rong+Ma%2C+Peiyi+Wang%2C+Xiao+Bi%2C+and+1+others%2E+2025%2E)
22. Shehenaz Hossain and Haithem Afli. 2025. Adapt– mtu hai at qias2025: Dualexpert llm finetuning and constrained decoding for arabic islamic inheritance reasoning. In Proceedings of The Third Arabic Nat ural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shehenaz+Hossain+and+Haithem+Afli%2E+2025%2E+Adapt%E2%80%93+mtu+hai+at+qias2025%3A+Dualexpert+llm+finetuning+and+constrained+decoding+for+arabic+islamic+inheritance+reasoning%2E+In+Proceedings+of+The+Third+Arabic+Nat)
23. Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Dingjie Song, Zhihong Chen, Abdulmohsen Alharthi, Bang An, Juncai He, and 1 others. 2023. [Acegpt, localizing large language models in arabic](https://md.research.elamur.ai/free/en/papers/huang-2024-acegpt-localizing-large-language-models/). arXiv preprint arXiv:2309.12053. [↗](https://arxiv.org/abs/2309.12053)
24. Anis Koubaa, Adel Ammar, Lahouari Ghouti, Omar Na jar, and Serry Sibaee. 2024. [Arabiangpt: Native ara bic gptbased large language model](https://md.research.elamur.ai/free/en/papers/koubaa-2024-arabiangpt-native-arabic-gpt-based/). arXiv preprint arXiv:2402.15313. [↗](https://arxiv.org/abs/2402.15313)
25. Rana Malhas, Watheq Mansour, and Tamer Elsayed. 2022. [find](https://scholar.google.com/scholar?q=Rana+Malhas%2C+Watheq+Mansour%2C+and+Tamer+Elsayed%2E+2022%2E)
26. Qur’an QA 2022: [Overview of the first shared task on question answering over the holy qur’an](https://md.research.elamur.ai/free/en/papers/malhas-2022-qur-qa-2022-overview-first/). In Proceedings of the 5th Workshop on OpenSource Arabic Corpora and Processing Tools, pages 79–87, Marseille, France. European Language Resources As sociation.
27. Rana Malhas, Watheq Mansour, and Tamer Elsayed. 2023. [Qur’an qa 2023 shared task: Overview of passage retrieval and reading comprehension tasks over the holy qur’an](https://md.research.elamur.ai/free/en/papers/malhas-2023-qur-qa-2023-shared-task/). In Proceedings of ArabicNLP 2023, pages 690–701, Singapore.
28. Marryam Yahya Mohammed, Sama Ayman Ali, Salma Khaled Ali, Ayad Abdul Majeed, and En saf Hussein Mohamed. 2025. Aftina: enhancing stability and preventing hallucination in aibased is lamic fatwa generation using llms and rag. Neural Computing and Applications, pages 1–26. [find](https://scholar.google.com/scholar?q=Marryam+Yahya+Mohammed%2C+Sama+Ayman+Ali%2C+Salma+Khaled+Ali%2C+Ayad+Abdul+Majeed%2C+and+En+saf+Hussein+Mohamed%2E+2025%2E+Aftina%3A+enhancing+stability+and+preventing+hallucination+in+aibased+is+lamic+fatwa+genera)
29. Yossra Noureldien, Hassan Suliman, Farah Attallah, Ab delrazig Mohamed, and Sara Abdalla. 2025. Athar at qias2025: Mcqsbased question answering systems for islamic inheritance and classical knowledge. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yossra+Noureldien%2C+Hassan+Suliman%2C+Farah+Attallah%2C+Ab+delrazig+Mohamed%2C+and+Sara+Abdalla%2E+2025%2E+Athar+at+qias2025%3A+Mcqsbased+question+answering+systems+for+islamic+inheritance+and+classical+knowledge%2E)
30. Nguyen Xuan Phuc and Thìn Đặng Văn. 2025. Puxai at qias 2025: Multiagent retrievalaugmented gen eration for islamic inheritance and knowledge rea soning. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Lin guistics. [find](https://scholar.google.com/scholar?q=Nguyen+Xuan+Phuc+and+Th%C3%ACn+%C4%90%E1%BA%B7ng+V%C4%83n%2E+2025%2E+Puxai+at+qias+2025%3A+Multiagent+retrievalaugmented+gen+eration+for+islamic+inheritance+and+knowledge+rea+soning%2E+In+Proceedings+of+The+Third+Arabic+Natural+Lan)
31. Faiza Qamar, Seemab Latif, and Rabia Latif. 2024. A benchmark dataset with larger context for nonfactoid question answering over islamic text. arXiv preprint arXiv:2409.09844. [↗](https://arxiv.org/abs/2409.09844)
32. Samia Zouaoui and Khaled Rezeg. 2021. Islamic in heritance calculation system based on arabic ontol ogy (arafamonto). Journal of King Saud University Computer and Information Sciences, 33(1):68–76. [find](https://scholar.google.com/scholar?q=Samia+Zouaoui+and+Khaled+Rezeg%2E+2021%2E+Islamic+in+heritance+calculation+system+based+on+arabic+ontol+ogy+%28arafamonto%29%2E+Journal+of+King+Saud+University+Computer+and+Information+Sciences%2C+33%281%29%3A68%E2%80%9376%2E)
33. Jihad R’baiti, Chouaib El Hachimi, Youssef Hmamouche, and Amal Seghrouchni. 2025. Morai at qias 2025: Collaborative llm via voting and retrievalaugmented generation for solving complex inheritance problems. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jihad+R%E2%80%99baiti%2C+Chouaib+El+Hachimi%2C+Youssef+Hmamouche%2C+and+Amal+Seghrouchni%2E+2025%2E+Morai+at+qias+2025%3A+Collaborative+llm+via+voting+and+retrievalaugmented+generation+for+solving+complex+inheritance+pro)
34. Muhammad Razif Rizqullah, Ayu Purwarianti, and Al ham Fikri Aji. 2023. Qasina: Religious domain ques tion answering using sirah nabawiyah. In 2023 10th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), pages 1–6. [find](https://scholar.google.com/scholar?q=Muhammad+Razif+Rizqullah%2C+Ayu+Purwarianti%2C+and+Al+ham+Fikri+Aji%2E+2023%2E+Qasina%3A+Religious+domain+ques+tion+answering+using+sirah+nabawiyah%2E+In+2023+10th+International+Conference+on+Advanced+Informatics)
35. Mohamed Samy, Mayar Boghdady, Marwan El Adawi, Mohamed Nassar, and Ensaf Hussein. 2025. Tok enizers united at qias 2025: Ragenhanced question answering for islamic studies by integrating semantic retrieval with generative reasoning. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Asso ciation for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mohamed+Samy%2C+Mayar+Boghdady%2C+Marwan+El+Adawi%2C+Mohamed+Nassar%2C+and+Ensaf+Hussein%2E+2025%2E+Tok+enizers+united+at+qias+2025%3A+Ragenhanced+question+answering+for+islamic+studies+by+integrating+semantic+retr)
36. Mohammad Amaan Sayeed, Mohammed Talha Alam, Raza Imam, Shahab Saquib Sohail, and Amir Hus sain. 2025. From rag to agentic: Validating islamic medicine responses with llm agents. arXiv preprint arXiv:2506.15911. [↗](https://arxiv.org/abs/2506.15911)
37. Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, William Marshall, Gurpreet Gosal, Cynthia Liu, Zhiming Chen, and 1 others. 2023. [Jais and jaischat: Arabic centric foundation and instructiontuned open gen erative large language models](https://md.research.elamur.ai/free/en/papers/sengupta-2023-jais-jais-chat-arabic-centric/). arXiv preprint arXiv:2308.16149. [↗](https://arxiv.org/abs/2308.16149)
38. Serry Sibaee, Mahmoud Reda, Omer Nacar, Yasser Alhabashi, Adel Ammar, and Wadii Boulila. 2025. Anlpers at qias 2025: Cot for islamic inheritance. In Proceedings of The Third Arabic Natural Language Processing Conference (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Serry+Sibaee%2C+Mahmoud+Reda%2C+Omer+Nacar%2C+Yasser+Alhabashi%2C+Adel+Ammar%2C+and+Wadii+Boulila%2E+2025%2E+Anlpers+at+qias+2025%3A+Cot+for+islamic+inheritance%2E+In+Proceedings+of+The+Third+Arabic+Natural+Language+Pr)
39. Sadia Tabassum, AHM Hoque, Sharaban Twahura, and Mohammad Osiur Rahman. 2019. Developing an islamic farayez system applying software engineering. Jurnal Kejuruteraan, 31(1):25–38. [↗](https://doi.org/10.17576/jkukm-2019-31(1)-04)
40. Osama Zaki, Asmaa Badawy, Nada Elgewily, and Ahmed Sharaf. 2025. Cisrg at qias 2025: Assessing large language models on islamic legal reasoning and mathematical calculations. In Proceedings of The Third Arabic Natural Language Processing Confer ence (ArabicNLP 2025), Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Osama+Zaki%2C+Asmaa+Badawy%2C+Nada+Elgewily%2C+and+Ahmed+Sharaf%2E+2025%2E+Cisrg+at+qias+2025%3A+Assessing+large+language+models+on+islamic+legal+reasoning+and+mathematical+calculations%2E+In+Proceedings+of+The+Thi)

*Updated 1 November 2026*