Multi-objective math problem generation using large language model through an adaptive multi-level retrieval augmentation framework

Jianwen Sun, Wangzi Shi, Xiaoxuan Shen, Shengyingjie Liu, Luona Wei, Qian Wan

Abstract: Highlights•First study considering multiple objectives on math problem generation process.•An efficient and accurate adaptive multi-level retrieval augmentation framework.•Plug-and-play framework enhances math problem generation without parameter tuning.•New Chinese dataset with 9,000 samples provides benchmark for future research.