# Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs

Source: [Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs](<https://www.sota2.com/research/paper/68fa7a881e209131cea83b9e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:22:00.744Z

Authors: Mohamed Basem, Islam Oshallah, Ali Hamdi, Ammar Mohammed

Published: 2025-08-08T08:02:59.000Z

## Abstract

This paper presents two effective approaches for Extractive Question Answering (QA) on the Quran. It addresses challenges related to complex language, unique terminology, and deep meaning in the text. The second uses few-shot prompting with instruction-tuned large language models such as Gemini and DeepSeek. A specialized Arabic prompt framework is developed for span extraction. A strong post-processing system integrates subword alignment, overlap suppression, and semantic filtering. This improves precision and reduces hallucinations. Evaluations show that large language models with Arabic instructions outperform traditional fine-tuned models. The best configuration achieves a pAP10 score of 0.637. The results confirm that prompt-based instruction tuning is effective for low-resource, semantically rich QA tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.06103>)

[PDF](<https://arxiv.org/pdf/2508.06103.pdf>)
