M Wang, J Deng - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We consider the task of automated theorem proving, a key AI task. Deep learning has shown promise for training theorem provers, but there are limited human-written theorems and …
Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods …
V Firoiu, E Aygun, A Anand, Z Ahmed, X Glorot… - arXiv preprint arXiv …, 2021 - arxiv.org
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning …
A well-defined benchmark is essential for measuring and accelerating research progress of machine learning models. In this paper, we present a benchmark for high-level …
B Gao, Z Cai, R Xu, P Wang, C Zheng, R Lin… - arXiv preprint arXiv …, 2024 - arxiv.org
Mathematical verfier achieves success in mathematical reasoning tasks by validating the correctness of solutions. However, existing verifiers are trained with binary classification …
C Zhao, M Silva, S Poulsen - arXiv preprint arXiv:2406.10268, 2024 - arxiv.org
In mathematical proof education, there remains a need for interventions that help students learn to write mathematical proofs. Research has shown that timely feedback can be very …
Theorem proving is a fundamental task in mathematics. With the advent of large language models (LLMs) and interactive theorem provers (ITPs) like Lean, there has been growing …
M Pantsar - European Journal for Philosophy of Science, 2024 - Springer
Computer assisted theorem proving is an increasingly important part of mathematical methodology, as well as a long-standing topic in artificial intelligence (AI) research …
E Aygün, Z Ahmed, A Anand, V Firoiu, X Glorot… - arXiv preprint arXiv …, 2020 - arxiv.org
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning …