使用指令微调LLM进行抽取式古兰经QA的少样本提示
Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs
AI总结：
本文提出使用少样本提示与指令微调LLM进行《古兰经》抽取式问答，结合阿拉伯语提示框架和后处理系统，有效提升了精确度并减少了幻觉，最佳配置达到0.637的pAP10分数。
摘要：
本文提出了两种用于《古兰经》抽取式问答（QA）的有效方法。它解决了文本中复杂语言、独特术语和深层含义相关的挑战。第二种方法使用少样本提示与指令微调大型语言模型（如Gemini和DeepSeek）。开发了专门的阿拉伯语提示框架用于片段抽取。强大的后处理系统集成了子词对齐、重叠抑制和语义过滤。这提高了精确度并减少了幻觉。评估表明，带有阿拉伯语指令的大型语言模型优于传统的微调模型。最佳配置实现了0.637的pAP10分数。结果证实，基于提示的指令微调对于低资源、语义丰富的QA任务是有效的。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
