Silah at QIAS 2026: Fine-Tuning vs. Retrieval-Augmented Generation for Islamic Inheritance Reasoning
Year: 2026
Type: conference-paper
Abstract: Islamic inheritance is a highly structured, rule-intensive domain that requires precise reasoning.The QIAS 2026 shared task introduces a benchmark for evaluating generative artificial intelligence on end-to-end inheritance problem solving.In this paper, we present our team Silah's participation, comparing three approaches: 1) a multi-stage retrieval-augmented, rule-guided pipeline, 2) supervised fine-tuning of generative large language models, and 3) retrieval-augmented fine-tuning.We evaluate several open-source models, including Qwen2.5, LLaMA, DeepSeek, and Fanar.Our results show that supervised fine-tuning consistently outperforms retrieval-based approaches, with the fine-tuned Fanar-1-9B-Instruct model achieving the best performance (MIR-E = 0.83).These findings suggest that learning implicit reasoning patterns through fine-tuning is more effective than explicit rule injection under current retrieval setups, highlighting the need for more precise and selective rule retrieval in future approaches.
Institution: Umm al-Qura University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166580230