Skip to yearly menu bar Skip to main content


Magnushammer: A Transformer-Based Approach to Premise Selection

Maciej Mikuła · Szymon Tworkowski · Szymon Antoniak · Bartosz Piotrowski · Qiaochu Jiang · Jin Zhou · Christian Szegedy · Łukasz Kuciński · Piotr Miłoś · Yuhuai Wu

Halle B #59
[ ]
Thu 9 May 1:45 a.m. PDT — 3:45 a.m. PDT

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 knowledge or feature engineering overhead. Our method, Magnushammer, outperforms the most advanced and widely used automation tool in interactive theorem proving called Sledgehammer. On the PISA and miniF2f benchmarks Magnushammer achieves $59.5\%$ (against $38.3\%$) and $34.0\%$ (against $20.9\%$) success rates, respectively. By combining Magnushammer with a language-model-based automated theorem prover, we further improve the state-of-the-art proof success rate from $57.0\%$ to $71.0\%$ on the PISA benchmark using $4$x fewer parameters. Moreover, we develop and open source a novel dataset for premise selection, containing textual representations of (proof state, relevant premise) pairs. To the best of our knowledge, this is the largest available premise selection dataset, and the first dataset of this kind for the Isabelle proof assistant.

Chat is not available.