CIS-RG at QIAS 2025 Shared Task: Approaches for Enhancing Performance of LLM on Islamic Legal Reasoning and its Mathematical Calculations
Year: 2025
Type: conference-paper
Abstract: The work in this paper is related to the shared task QIAS2025.In this paper we continue in assessing large language models on Islamic legal reasoning.It is a challenging task because LLMs have not yet evolved (especially the open-source models) to solve complex reasoning problems or to perform mathematical calculations that require several steps.The LLMs need to comprehend the problem and to generate accurate and justified answers.In this paper we confirm the results and the analysis given in (Bouchekif, 2024; Bouchekif, 2025).However, we experiment further with Fine Tuning and Chain of Thought (CoT) to improve the performance of the reasoning process and therefor the results of the LLMs.
Author: Osama Farouk Zaki
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4416037623