CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance Reasoning
This work addresses the problem of automating Islamic inheritance reasoning for legal or religious applications, but it is incremental as it focuses on optimizing efficiency rather than achieving state-of-the-art accuracy.
The paper tackled the challenge of applying AI to Islamic inheritance law by developing a lightweight framework using a specialized Arabic text encoder and Attentive Relevance Scoring for multiple-choice questions, achieving 69.87% accuracy on the QIAS 2025 dataset, which is lower than the 87.6% from large models but emphasizes efficiency and on-device deployability.
Islamic inheritance law (Ilm al-Mawarith) requires precise identification of heirs and calculation of shares, which poses a challenge for AI. In this paper, we present a lightweight framework for solving multiple-choice inheritance questions using a specialised Arabic text encoder and Attentive Relevance Scoring (ARS). The system ranks answer options according to semantic relevance, and enables fast, on-device inference without generative reasoning. We evaluate Arabic encoders (MARBERT, ArabicBERT, AraBERT) and compare them with API-based LLMs (Gemini, DeepSeek) on the QIAS 2025 dataset. While large models achieve an accuracy of up to 87.6%, they require more resources and are context-dependent. Our MARBERT-based approach achieves 69.87% accuracy, presenting a compelling case for efficiency, on-device deployability, and privacy. While this is lower than the 87.6% achieved by the best-performing LLM, our work quantifies a critical trade-off between the peak performance of large models and the practical advantages of smaller, specialized systems in high-stakes domains.