Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908482220851200 |
|---|---|
| author | Basem, Mohamed Oshallah, Islam Hamdi, Ali Mohammed, Ammar |
| author_facet | Basem, Mohamed Oshallah, Islam Hamdi, Ali Mohammed, Ammar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06103 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs Basem, Mohamed Oshallah, Islam Hamdi, Ali Mohammed, Ammar Computation and Language Information Retrieval 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. |
| title | Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2508.06103 |