---
title: "PSL at QIAS 2026 — paper by Mohammed and Bouchekif (2026)"
description: "The authors did not build a specialised pipeline. 19 references, cited by 3 papers here. Among them: 0."
authors: ["amine Mohammed", "Chahinez Bouchekif"]
year: 2026
venue: "The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks"
source: "https://aclanthology.org/2026.osact-1.25/"
doi: "10.63317/3q67jok59yam"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/mohammed-2026-psl-qias-2026-which-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mohammed-2026-psl-qias-2026-which-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/) / PSL at QIAS 2026: Which Models Perform Better in Arabic Inheritance Reasoning?

# PSL at QIAS 2026: Which Models Perform Better in Arabic Inheritance Reasoning?

**Authors:** amine Mohammed and Chahinez Bouchekif · **Year:** 2026 · **Venue:** [The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks](https://md.research.elamur.ai/free/en/venues/osact/) ([Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks 2026](https://md.research.elamur.ai/free/en/venues/osact/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.osact-1.25/) · [PDF](https://aclanthology.org/2026.osact-1.25.pdf) · [DOI 10.63317/3q67jok59yam](https://doi.org/10.63317/3q67jok59yam) · [OpenAlex](https://openalex.org/W7166522000)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/mohammed-2026-psl-qias-2026-which-models/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Team PSL took part in the QIAS 2026 shared task, which tests whether LLMs can solve Islamic inheritance ('ilm al-mawārīth) cases written in Arabic. These cases require identifying eligible heirs, applying blocking rules, assigning fixed shares and, when needed, applying 'awl or radd adjustments. The authors did not build a specialised pipeline. They gave commercial and open-source models one shared step-by-step chain-of-thought prompt, a fixed output format, and only light post-processing to normalise heir names. They tested this on the QIAS 2026 benchmark of 12,500 cases, which follows the majority (al-jumhūr) juristic view. The gap between the two groups was large. The Gemini models scored around 0.9 MIR-E, while the best open-source model, Qwen3-32B, reached only about 45 (on a 0–100 scale). Manual error analysis showed that open-source models tend to make early mistakes, such as dropping or inventing heirs, and these errors carry through to the final shares. Fluent output was often still legally wrong. The work offers a clean, like-for-like baseline for how well general-purpose models handle structured legal reasoning in Arabic.

## Key points
- **Data:** the QIAS 2026 data has 12,000 training and 500 test cases and covers 36 heir categories, with up to 12 per case. The training split contains 11,079 simple, 577 'awl and 344 radd cases. Each case includes a reasoning trace and a final answer.
- **Models tested:**
  - Commercial: Gemini 2.5 Pro and Gemini 2.5 Flash.
  - Open-source: Qwen3-32B, GPT-oss-120B, Llama-3.3-70B, Fanar-Sadiq and Fanar-C-2-27B.
  - Falcon3-10B-Instruct was dropped because it did not follow the prompt instructions.
- **Table 1 (MIR-E):** Gemini-2.5-Pro scored 0.931 and Gemini-2.5-Flash scored 0.898 (official submission). The open-source models scored 45.1, 38.7, 35.9, 35.8 and 33.1, apparently on a percentage scale.
- **Inconsistency in the paper:** the abstract reports Gemini 2.5 Flash as the best model with an MRE of 0.989, which does not match Table 1.
- **Ranking and errors:** PSL placed 5th in the official ranking. Other teams used RAG, fine-tuning and hybrid symbolic methods. The most common errors were missing or hallucinated heirs, wrong exclusion rules and infeasible share allocations.

*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

- [University of Abou Bekr Belkaïd](https://md.research.elamur.ai/free/en/universities/university-of-abou-bekr-belkaid/) — University, Tlemcen, Algeria · 2 works · 21 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 · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: amine Mohammed and Chahinez Bouchekif. 2026. PSL at QIAS 2026: Which Models Perform Better in Arabic Inheritance Reasoning?. The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks.

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

```bibtex
@inproceedings{mohammed2026psl,
  title = {{PSL at QIAS 2026: Which Models Perform Better in Arabic Inheritance Reasoning?}},
  author = {amine Mohammed and Chahinez Bouchekif},
  booktitle = {The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks},
  year = {2026},
  doi = {10.63317/3q67jok59yam},
  url = {https://doi.org/10.63317/3q67jok59yam}
}
```

- [← previous Protecting multimodal large language models against misleading visualizations](https://md.research.elamur.ai/free/en/papers/tonglet-2026-protecting-multimodal-large-language-models/)
- [next → QIAS 2026: Overview of the Shared Task on Islamic Inheritance Reasoning](https://md.research.elamur.ai/free/en/papers/bouchekif-2026-qias-2026-overview-shared-task/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

19 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. This also explains why good instruction-following is not enough. A model can follow the prompt and produce a clear and convincing explanation, but still make mistakes in the legal structure of the solution. Another possible reason for the low performance of Arabic-oriented models is that they are not trained on this type of structured reasoning. Inheritance problems require specific logical steps and rule-based decisions, which may not be well represented in their training data. In this context, the QIAS 2026 dataset can be very useful. It provides examples of Islamic inheritance reasoning that could help models learn this type of task and improve their performance. 5. Conclusion This paper presented the participation of team PSL in the QIAS 2026 Shared Task on Arabic Islamic inheritance reasoning. Our submission focused on a controlled comparison between commercial and open-source language models under a shared prompting framework. The experiments showed that commercial models remain clearly stronger on this task, especially when the case requires several dependent legal decisions and precise numerical consistency. Open-source models show promise, but they still suffer from frequent structural errors that propagate across the reasoning chain. More broadly, our findings confirm that Islamic inheritance is a demanding testbed for evaluating legal reasoning in Arabic. In future work, we plan to explore stronger output constraints, step-level verification, and domain-adapted training strategies to improve consistency on this class of tasks. We also believe that combining LLMs with explicit reasoning checks may be a promising direction for legal and rule-based NLP more generally. Acknowledgments We would like to thank the organizers of QIAS 2026 for their efforts in designing and running the shared task. In particular, we are grateful to Dr. Abdessalam Bouchekif for his guidance and support. [find](https://scholar.google.com/scholar?q=This+also+explains+why+good+instruction%2Dfollowing+is+not+enough%2E+A+model+can+follow+the+prompt+and+produce+a+clear+and+convincing+explanation%2C+but+still+make+mistakes+in+the+legal+structure+of+the+sol)
2. Mohammad AL-Smadi. 2025. [QU-NLP at QIAS 2025 shared task: A two-phase LLM fine-tuning and retrieval-augmented generation approach for islamic inheritance reasoning](https://md.research.elamur.ai/free/en/papers/smadi-2025-qu-nlp-qias-2025-shared/). In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 892–898, Suzhou, China. Association for Computational Linguistics.
3. 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 Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 861–866, Suzhou, China. Association for Computational Linguistics.
4. Omar Alkhamis. 2026. KMS at QIAS 2026: Comparing LLM reasoning and hybrid symbolic solving for islamic inheritance division. In Proceedings of the 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7), co-located with LREC-COLING 2026, Palma de Mallorca, Spain. [find](https://scholar.google.com/scholar?q=Omar+Alkhamis%2E+2026%2E+KMS+at+QIAS+2026%3A+Comparing+LLM+reasoning+and+hybrid+symbolic+solving+for+islamic+inheritance+division%2E+In+Proceedings+of+the+7th+Workshop+on+Open%2DSource+Arabic+Corpora+and+Proces)
5. Muath Almansour. 2026. Simplicity at QIAS 2026: Decoupling language extraction from mathematical logic in islamic inheritance law. In Proceedings of the 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7), co-located with LREC-COLING 2026, Palma de Mallorca, Spain. [find](https://scholar.google.com/scholar?q=Muath+Almansour%2E+2026%2E+Simplicity+at+QIAS+2026%3A+Decoupling+language+extraction+from+mathematical+logic+in+islamic+inheritance+law%2E+In+Proceedings+of+the+7th+Workshop+on+Open%2DSource+Arabic+Corpora+and+)
6. Mohammad Alsmadi. 2026. [QU-NLP at QIAS 2026: Multi-stage QLoRA fine-tuning for arabic islamic inheritance reasoning](https://md.research.elamur.ai/free/en/papers/alsmadi-2026-qu-nlp-qias-2026-multi/). In Proceedings of the 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7), co-located with LREC-COLING 2026, Palma de Mallorca, Spain.
7. Abdessalam Bouchekif, Shahd Gaben, Samer Rashwani, Somaya Eltanbouly, Mutaz Al-Khatib, Heba Sbahi, Mohammed Ghaly, and Emad Mohamed. 2026. [Mawarith: A dataset and benchmark for legal inheritance reasoning with llms](https://md.research.elamur.ai/free/en/papers/bouchekif-2026-mawarith-dataset-benchmark-legal-inheritance/). arXiv preprint arXiv:2603.07539. [↗](https://arxiv.org/abs/2603.07539)
8. Abdessalam Bouchekif, Samer Rashwani, Emad Soliman Ali Mohamed, Mutaz Alkhatib, Heba Sbahi, Shahd Gaben, Wajdi Zaghouani, Aiman Erbad, and Mohammed Ghaly. 2025a. [QIAS 2025: Overview of the shared task on islamic inheritance reasoning and knowledge assessment](https://md.research.elamur.ai/free/en/papers/bouchekif-2025-qias-2025-overview-shared-task/). In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 851–860.
9. Abdessalam Bouchekif, Samer Rashwani, Heba Sbahi, Shahd Gaben, Mutaz Al Khatib, and Mohammed Ghaly. 2025b. [Assessing large language models on islamic legal reasoning: Evidence from inheritance law evaluation](https://md.research.elamur.ai/free/en/papers/bouchekif-2025-assessing-large-language-models-islamic/). In Proceedings of The Third Arabic Natural Language Processing Conference, pages 246–257.
10. Salah Eddine Bekhouche, Abdellah Zakaria Sellam, Telli Hichem, Cosimo Distante, and Abdenour Hadid. 2025. [CVPD at QIAS 2025 shared task: An efficient encoder-based approach for islamic inheritance reasoning](https://md.research.elamur.ai/free/en/papers/bekhouche-2025-cvpd-qias-2025-shared-task/). In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 929–934, Suzhou, China. Association for Computational Linguistics.
11. Eman Elrefai, Mohamed Lotfy Elrefai, and Aml Hassan Esmail. 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 Natural Language Processing Conference: Shared Tasks, pages 953–959, Suzhou, China. Association for Computational Linguistics.
12. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [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/). arXiv preprint arXiv:2501.12948. [↗](https://arxiv.org/abs/2501.12948)
13. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. 2024. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720. [↗](https://arxiv.org/abs/2412.16720)
14. Ghader Kurdi, Hanan Justanieah, and Hala Justanieah. 2026. [Silah at QIAS 2026: Fine-tuning vs. retrieval-augmented generation for islamic inheritance reasoning](https://md.research.elamur.ai/free/en/papers/kurdi-2026-silah-qias-2026-fine-tuning/). In Proceedings of the 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7), co-located with LREC-COLING 2026, Palma de Mallorca, Spain.
15. Hicham Ghazi Sidaoui. 2026. [AGS-KSU at QIAS 2026: A comparative study of prompting and LLM approaches for structured islamic inheritance reasoning](https://md.research.elamur.ai/free/en/papers/sidaoui-2026-ags-ksu-qias-2026-comparative/). In Proceedings of the 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7), co-located with LREC-COLING 2026, Palma de Mallorca, Spain.
16. Wassim Swaileh, Mohammed-En-Nadhir Zighem, Hichem Telli, Salah Eddine Bekhouche, Abdellah Zakaria Sellam, and Fadi Dornaika. 2026. CVPD at QIAS 2026: RAG-guided LLM reasoning for al-mawarith share calculation and heir allocation. In Proceedings of the 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7), co-located with LREC-COLING 2026, Palma de Mallorca, Spain. [find](https://scholar.google.com/scholar?q=Wassim+Swaileh%2C+Mohammed%2DEn%2DNadhir+Zighem%2C+Hichem+Telli%2C+Salah+Eddine+Bekhouche%2C+Abdellah+Zakaria+Sellam%2C+and+Fadi+Dornaika%2E+2026%2E+CVPD+at+QIAS+2026%3A+RAG%2Dguided+LLM+reasoning+for+al%2Dmawarith+share+cal)
17. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171. [↗](https://arxiv.org/abs/2203.11171)
18. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). arXiv preprint arXiv:2201.11903. [↗](https://arxiv.org/abs/2201.11903)
19. Nguyen Xuan Phuc and Thìn Ðng Văn. 2025. [PuxAI at QIAS 2025: Multi-agent retrieval-augmented generation for islamic inheritance and knowledge reasoning](https://md.research.elamur.ai/free/en/papers/phuc-2025-puxai-qias-2025-multi-agent/). In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks, pages 905–913, Suzhou, China. Association for Computational Linguistics.

*Updated 1 November 2026*