Large Language Models in Mathematical Intelligent Educational Assessment: A Literature Review

Xu Tong, Razali Yaakob and Sina Abdipoor

With the in-depth integration of artificial intelligence and education, Large Language Models (LLMs) have become a new technical support for the innovation of mathematical intelligent educational assessment. This literature review systematically sorts out research on the application of LLMs in mathematical intelligent educational assessment, focusing on four core aspects: application status, core technology optimization, existing research achievements and dataset support. A systematic literature retrieval method was adopted. Through critical analysis of relevant literature and comparative study of core journals in the field, this review identifies five key research gaps in current studies, including insufficient subject adaptability of LLMs in mathematics, low feedback quality, imperfect adaptive learning closed loop, single teacher assistance function and insufficient integrated application of mathematical datasets. Finally, based on these gaps, the future research direction of this field is clarified and promotes the in-depth application of LLMs in mathematics education scenarios.

View Fulltext Back