# QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning

arXiv: https://arxiv.org/abs/2508.15854 · HTML: https://mlsanity.com/paper/2508.15854/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 8 of 8)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models](https://mlsanity.com/paper/2308.16149/) (2023)
- [Fanar: An Arabic-Centric Multimodal Generative AI Platform](https://mlsanity.com/paper/2501.13944/) (2025)
- [ALLaM: Large Language Models for Arabic and English](https://mlsanity.com/paper/2407.15390/) (2024)
- [Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS](https://mlsanity.com/paper/2401.15378/) (2024)
- [From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents](https://mlsanity.com/paper/2506.15911/) (2025)

## Built on by (most cited first, 4 of 4)

- [MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs](https://mlsanity.com/paper/2603.07539/) (2026)
- [IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions](https://mlsanity.com/paper/2602.21226/) (2026)
- [QIAS 2026: Overview of the Shared Task on Islamic Inheritance Reasoning](https://mlsanity.com/paper/2606.13756/) (2026)
- [Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA](https://mlsanity.com/paper/2603.08501/) (2026)

## Abstract (arXiv)

This paper presents our approach and results for SubTask 1: Islamic Inheritance Reasoning at QIAS 2025, a shared task focused on evaluating Large Language Models (LLMs) in understanding and reasoning within Islamic inheritance knowledge. We fine-tuned the Fanar-1-9B causal language model using Low-Rank Adaptation (LoRA) and integrated it into a Retrieval-Augmented Generation (RAG) pipeline. Our system addresses the complexities of Islamic inheritance law, including comprehending inheritance scenarios, identifying eligible heirs, applying fixed-share rules, and performing precise calculations. Our system achieved an accuracy of 0.858 in the final test, outperforming other competitive models such as, GPT 4.5, LLaMA, Fanar, Mistral and ALLaM evaluated with zero-shot prompting. Our results demonstrate that QU-NLP achieves near state-of-the-art accuracy (85.8%), excelling especially on advanced reasoning (97.6%) where it outperforms Gemini 2.5 and OpenAI's o3. This highlights that domain-specific fine-tuning combined with retrieval grounding enables mid-scale Arabic LLMs to surpass frontier models in Islamic inheritance reasoning.