Portal de Periódicos da CAPES

Solving Probability and Statistics Problems by Probabilistic Program Synthesis at Human Level and Predicting Solvability

2022; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-3-031-11647-6_127

1611-3349

Leonard Tang, Elizabeth Ke, Nikhil Singh, Bo Feng, Derek Austin, Nakul Verma, Iddo Drori,

Computational Physics and Python Applications

We use probabilistic program synthesis to solve questions in MIT and Harvard Probability and Statistics courses. Traditional approaches using the latest GPT-3 language model without program synthesis achieve a solve rate of 0.2 in these classes. In contrast, by turning course questions into probabilistic programs using the latest program synthesis Transformer, OpenAI Codex, and executing the programs, our solve rates are 0.9 and 0.88, which are on par with human performance.