@inproceedings{alsmadi-2026-qu,
    title = "{QU}-{NLP} at {QIAS} 2026: Multi-Stage {QL}o{RA} Fine-Tuning for {A}rabic Islamic Inheritance Reasoning",
    author = "ALSmadi, Mohammad",
    editor = "Al-Khalifa, Hend  and
      El-Haj, Mo  and
      Ezzini, Saad",
    booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/revision-workflow/2026.osact-1.24/",
    doi = "10.63317/2xw2ocj47xav",
    pages = "199--203",
    abstract = "Islamic inheritance law (علم المواريث, ilm al-mawar{\i}th) presents a challenging domain for evaluating large language models' structured reasoning capabilities, requiring multi-step legal analysis, rule-based blocking decisions, and precise fractional calculations. We present QU-NLP{'}s submission to the QIAS 2026 shared task on Arabic Islamic inheritance reasoning. Our approach employs a multi-stage Quantized Low-Rank Adaptation (QLoRA) fine-tuning strategy on Qwen3-4B: (1) domain adaptation on 3,166 Islamic fatwa records to acquire inheritance terminology and jurisprudential reasoning patterns, followed by (2) task-specific training on 12,000 structured inheritance cases to optimize JSON-formatted output generation. Using 4-bit NF4 quantization with rank-128 LoRA adapters, our model achieves 90{\%} MIR-E (Mawarith Inheritance Reasoning Evaluation) score on the test set, demonstrating competitive performance while requiring minimal computational resources. Our results show that domain-specific pre-adaptation combined with structured output training enables small language models to perform complex legal reasoning tasks effectively comparing to commercial systems such as Gemini-2.5-flash."
}