Silah at QIAS 2026: Fine-Tuning vs. Retrieval-Augmented Generation for Islamic Inheritance Reasoning

Ghader Kurdi, Hanan Justanieah, Hala Justanieah


Abstract
Islamic inheritance is a highly structured and 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 in the QIAS 2026 shared task, where we compare three approaches: (1) a multi-stage retrieval-augmented, rule-guided pipeline, (2) supervised fine-tuning of generative large language models, and (3) a retrieval-augmented fine-tuning approach. 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) and ranking sixth overall in the shared task. These findings suggest that learning implicit reasoning patterns through fine-tuning is more effective than explicit rule injection under current retrieval setups, and emphasize the need for more accurate and minimal rule selection mechanisms in future retrieval-augmented approaches.
Anthology ID:
2026.osact-1.27
Volume:
The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Hend Al-Khalifa, Mo El-Haj, Saad Ezzini
Venues:
OSACT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
213–219
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-osact-27
DOI:
10.63317/4iyrxakdovsm
Bibkey:
Cite (ACL):
Ghader Kurdi, Hanan Justanieah, and Hala Justanieah. 2026. Silah at QIAS 2026: Fine-Tuning vs. Retrieval-Augmented Generation for Islamic Inheritance Reasoning. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 213–219, Palma, Mallorca (Spain). Association for Computational Linguistics.
Cite (Informal):
Silah at QIAS 2026: Fine-Tuning vs. Retrieval-Augmented Generation for Islamic Inheritance Reasoning (Kurdi et al., OSACT 2026)
Copy Citation: