Mamo
收藏资源简介:
Mamo数据集是由香港中文大学(深圳)创建,专注于评估大型语言模型(LLMs)在数学建模中的能力。该数据集包含1059个精心设计的问题,涵盖普通微分方程和线性规划等优化问题。创建过程中,数据集结合了人工选择和GPT生成的题目,确保了问题的多样性和实用性。Mamo数据集的应用领域主要在于评估和提升LLMs在复杂问题解决场景中的数学建模能力,为人工智能领域提供了一个新的评估标准。
The Mamo dataset was developed by the Chinese University of Hong Kong, Shenzhen, focusing on evaluating the capabilities of Large Language Models (LLMs) in mathematical modeling. This dataset comprises 1059 meticulously designed questions covering optimization problems such as ordinary differential equations and linear programming. During its creation, the dataset combines manually selected questions and GPT-generated content to ensure the diversity and practicality of the problems. The main application scenarios of the Mamo dataset are to evaluate and enhance the mathematical modeling abilities of LLMs in complex problem-solving scenarios, providing a new evaluation benchmark for the field of artificial intelligence.




