1 Matching Annotations
 Feb 2022

arxiv.org arxiv.org

We provide the first demonstration that a neural network solvesuniversitylevel mathematics problems. Our methods combinetwo innovations: (i) recent neural networks pretrained on textand finetuned on code, rather than pretrained on text alone,and (ii) novel techniques to automatically rephrase problems soneural networks can synthesize correct executable programs.We generate programs that perfectly solve a random sampleof problems from MIT mathematics courses including Singleand Multivariable Calculus, Differential Equations, Probabilityand Statistics, Linear Algebra, and Mathematics for ComputerScience, as well as problems in the MATH benchmark of highschool math topics. Our methods also generate new questionsthat are indistinguishable by students from course questions.Implications for higher education include new roles of AI inautomatic course evaluation and content generation.
A neural network solves universitylevel mathematics problems (questions from MIT math courses).
Tags
Annotators
URL
