Proof Artifact Co-training for Theorem Proving with Language Models

Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built. This is particularly challenging when applying large Transformer language models to tactic prediction...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Han, Jesse Michael, Rute, Jason, Wu, Yuhuai, Ayers, Edward W, Polu, Stanislas
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Learning Computer Science - Logic in Computer Science
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!