Generative Language Modeling for Automated Theorem Proving

09/07/2020
by   Stanislas Polu, et al.
83

We explore the application of transformer-based language models to automated theorem proving. This work is motivated by the possibility that a major limitation of automated theorem provers compared to humans – the generation of original mathematical terms – might be addressable via generation from language models. We present an automated prover and proof assistant, GPT-f, for the Metamath formalization language, and analyze its performance. GPT-f found new short proofs that were accepted into the main Metamath library, which is to our knowledge, the first time a deep-learning based system has contributed proofs that were adopted by a formal mathematics community.

READ FULL TEXT
research
08/09/2018

Proof Simplification and Automated Theorem Proving

The proofs first generated by automated theorem provers are far from opt...
research
05/22/2022

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

In theorem proving, the task of selecting useful premises from a large l...
research
02/11/2021

Proof Artifact Co-training for Theorem Proving with Language Models

Labeled data for imitation learning of theorem proving in large librarie...
research
10/21/2022

Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

The formalization of existing mathematical proofs is a notoriously diffi...
research
06/14/2016

DeepMath - Deep Sequence Models for Premise Selection

We study the effectiveness of neural sequence models for premise selecti...
research
02/12/2020

Using Automated Theorem Provers for Mistake Diagnosis in the Didactics of Mathematics

The Diproche system, an automated proof checker for natural language pro...
research
03/05/2022

The Proof is in the Pudding: Using Automated Theorem Proving to Generate Cooking Recipes

This paper presents FASTFOOD, a rule-based Natural Language Generation P...

Please sign up or login with your details

Forgot password? Click here to reset