QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning
This addresses the problem of accurate Islamic inheritance law reasoning for legal/religious applications, showing domain-specific fine-tuning can surpass general frontier models.
The paper tackled Islamic inheritance reasoning by fine-tuning a 9B Arabic LLM with LoRA and integrating it into a RAG pipeline, achieving 85.8% accuracy and outperforming models like GPT-4.5 and Gemini 2.5 on advanced reasoning tasks.
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.