CHAMP
收藏资源简介:
CHAMP数据集由麻省理工学院计算机科学与人工智能实验室创建,包含270个高中数学竞赛题目,每个题目均附有概念和提示。数据集旨在评估大型语言模型在解决复杂数学问题时的推理能力,特别是如何利用额外的概念和提示信息。数据集中的问题涉及多个数学领域,如数论、多项式、序列、不等式和组合数学。通过此数据集,研究者可以探索模型如何处理和应用问题特定的提示,以及这些提示如何影响最终的解题结果。
The CHAMP dataset was developed by the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT). It contains 270 high school mathematics competition problems, each accompanied by corresponding conceptual explanations and hints. This dataset is designed to evaluate the reasoning capabilities of large language models (LLMs) when solving complex mathematical problems, specifically their capacity to leverage additional conceptual knowledge and hint information. The problems in the dataset span multiple mathematical domains, including number theory, polynomials, sequences, inequalities, and combinatorics. Using this dataset, researchers can investigate how models process and apply problem-specific prompts, as well as how these prompts affect the final problem-solving results.




