Magnushammer: A Transformer-Based Approach to Premise Selection

arXiv:2303.04488v3 Announce Type: replace
Abstract: This paper presents a novel approach to premise selection, a crucial reasoning task in automated theorem proving. Traditionally, symbolic methods that rely on extensive domain knowledge and engineering effort are applied to this task. In contrast, this work demonstrates that contrastive training with the transformer architecture can achieve higher-quality retrieval of relevant premises, without the engineering overhead. Our method, Magnushammer, outperforms the most advanced and widely used automation tool in interactive theorem proving called Sledgehammer. …

abstract architecture arxiv automated contrast cs.ai cs.lg cs.lo domain domain knowledge engineering knowledge novel paper reasoning theorem training transformer transformer architecture type work