作者位次 #4/8ACL 2026Findings· Findings of ACL
Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning
Jun Rao · Xuebo Liu · Hexuan Deng · Zepeng Lin · Zixiong Yu · Jiansheng Wei · Xiaojun Meng · Min Zhang
摘要
In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training. This misalignment limits the efficiency of Supervised Fine-Tuning and Reinforcement Learning. To bridge this g...