Autoformalization with large language models

Y Wu, AQ Jiang, W Li, M Rabe… - Advances in …, 2022 - proceedings.neurips.cc
Autoformalization is the process of automatically translating from natural language
mathematics to formal specifications and proofs. A successful autoformalization system …

Mathematical language models: A survey

W Liu, H Hu, J Zhou, Y Ding, J Li, J Zeng, M He… - arXiv preprint arXiv …, 2023 - arxiv.org
In recent years, there has been remarkable progress in leveraging Language Models (LMs),
encompassing Pre-trained Language Models (PLMs) and Large-scale Language Models …

The future is big graphs: a community view on graph processing systems

S Sakr, A Bonifati, H Voigt, A Iosup, K Ammar… - Communications of the …, 2021 - dl.acm.org
The future is big graphs: a community view on graph processing systems Page 1 62
COMMUNICATIONS OF THE ACM | SEPTEMBER 2021 | VOL. 64 | NO. 9 contributed articles …

Thor: Wielding hammers to integrate language models and automated theorem provers

AQ Jiang, W Li, S Tworkowski… - Advances in …, 2022 - proceedings.neurips.cc
In theorem proving, the task of selecting useful premises from a large library to unlock the
proof of a given conjecture is crucially important. This presents a challenge for all theorem …

A formal proof of the Kepler conjecture

T Hales, M Adams, G Bauer, TD Dang… - … of mathematics, Pi, 2017 - cambridge.org
A FORMAL PROOF OF THE KEPLER CONJECTURE Page 1 Forum of Mathematics, Pi (2017),
Vol. 5, e2, 29 pages doi:10.1017/fmp.2017.1 1 A FORMAL PROOF OF THE KEPLER …

The role of the Mizar Mathematical Library for interactive proof development in Mizar

G Bancerek, C Byliński, A Grabowski… - Journal of Automated …, 2018 - Springer
The Mizar system is one of the pioneering systems aimed at supporting mathematical proof
development on a computer that have laid the groundwork for and eventually have evolved …

The simplicial model of univalent foundations (after Voevodsky)

K Kapulkin, PLF Lumsdaine - Journal of the European Mathematical …, 2021 - ems.press
We present Voevodsky's construction of a model of univalent type theory in the category of
simplicial sets. To this end, we first give a general technique for constructing categorical …

Premise selection for theorem proving by deep graph embedding

M Wang, Y Tang, J Wang… - Advances in neural …, 2017 - proceedings.neurips.cc
We propose a deep learning-based approach to the problem of premise selection: selecting
mathematical statements relevant for proving a given conjecture. We represent a higher …

Learning to prove theorems via interacting with proof assistants

K Yang, J Deng - International Conference on Machine …, 2019 - proceedings.mlr.press
Humans prove theorems by relying on substantial high-level reasoning and problem-
specific insights. Proof assistants offer a formalism that resembles human mathematical …

[PDF][PDF] Hammering towards QED

JC Blanchette, C Kaliszyk, LC Paulson… - Journal of Formalized …, 2016 - pure.mpg.de
The main ingredients underlying this approach are efficient automatic theorem provers that
can cope with hundreds of axioms, suitable translations of the proof assistant's logic to the …