SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving
SMART: 自生成和自验证的多维评估用于LLM的数学问题解决
机构 * School of Artificial Intelligence, Beijing Normal University(北京师范大学人工智能学院) ; Beijing Key Laboratory of Artificial Intelligence for Education Engineering Research Center of Intelligent Technology and Educational Application, Ministry of Education(北京市教育厅人工智能教育工程研究中心智能技术与教育应用联合实验室)
专题命中 数学推理 :reasoning(abstract);分类 cs.AI
AI总结 SMART通过分解数学问题解决为四个维度,评估LLM的数学能力,揭示模型在不同维度上的差异,提出All-Pass Score衡量真实问题解决能力。
Comments Need to address additional data or methodological concerns