“The field is fairly new to me. I'm originally from computer algebra, and somehow struggling into the field of ATP. The most interesting papers to me personally are the following three: * Making higher order superposition work. https://doi.org/10.1007/978-3-030-79876-5_24 * MizAR 60 for Mizar 50. https://doi.org/10.48550/arXiv.2303.06686 * Magnus Hamme…”
Magnushammer: A Transformer-Based Approach to Premise Selection
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. On the PISA and miniF2F benchmarks Magnushammer achieves $59.5\%$ (against $38.3\%$) and $34.0\%$ (against $20.9\%$) success rates, respectively. By combining \method 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 one for the Isabelle proof assistant.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“About half of the problems in Compfiles have complete solutions. They are marked by the checkmarks in the list at https://dwrensha.github.io/compfiles/index.html. As far as I know, based on published systems like LeanDojo [1] and Magnushammer [2], computers today can only solve a small handful of the very easiest of these problems (like maybe Imo1959P1)…”
- Magnushammer: A Transformer-Based Approach to Premise Selection ↗jasondavies · 2023-03-09 · 2 分