arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.09830cs.CL
收藏

使用大型语言模型对阿拉伯语文本进行自动评分:文献综述

Automated Scoring of Arabic Text Using Large Language Models: A Literature Review

Laboratoire d’Informatique et de Mathématiques LIM, Amar Telidji University(阿马尔·特里吉大学计算机与数学实验室)

Khaoula Dahimi, Hadda Cherroun, Amel Belabbaci

AI总结:

本文综述了基于大型语言模型的阿拉伯语文本自动评分方法,包括简答题评分和作文评分,提出了包含五个维度的分类体系,并对比分析了现有研究的方法、数据集和性能。

摘要:

在现代教育系统中,自动文本评分(ATS)通过无需人工干预即可实现学习者回答的可扩展和一致评估,发挥着核心作用。最近,LLM和阿拉伯语特定数据集的可访问性增加,重新激发了这一领域的兴趣。在这项工作中,我们研究了基于LLM的阿拉伯语文本自动评估方法,重点关注简答题评分(ASAG)和作文评分(AES)。我们进一步引入了一个结构化的分类体系,包括五个维度:应用领域、反馈生成能力、部署的LLM架构、与能力参考框架的一致性以及提示工程策略。通过应用这一分类体系,我们对现有研究进行了比较分析,考察了它们的方法论、数据集、评估指标和报告的性能。研究结果强调了在阿拉伯语ATS领域开展持续且具有教育基础的研究努力的必要性,因为这对于提高阿拉伯语社区的教育质量具有重要意义。

英文摘要:

In modern educational systems, Automatic Text Scoring (ATS) plays a central role by enabling scalable and consistent evaluation of learner responses without human intervention. Recently, the increased accessibility of LLMs and Arabic-specific datasets has sparked renewed interest in this area. In this work, we investigate LLM-Based approaches for the automated evaluation of Arabic texts, focusing on both short answer grading (ASAG) and essay scoring (AES). We further introduce a structured taxonomy comprising five dimensions: application domain, feedback generation capability, LLM architecture deployed, alignment with competency referential frameworks, and prompt engineering strategy. By applying this taxonomy, we conduct a comparative analysis of existing studies, examining their methodological approaches, datasets, evaluation metrics, and reported performance. The findings highlight the need for sustained and pedagogically grounded research efforts in Arabic ATS, given its significance for improving educational quality across Arabic-speaking communities.

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。

↑