Automated Repair of Programs from Large Language Models

Large language models such as Codex, have shown the capability to produce code for many programming tasks. However, the success rate of existing models is low, especially for complex programming tasks. One of the reasons is that language models lack awareness of program semantics, resulting in incor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-01
Hauptverfasser:	Fan, Zhiyu, Gao, Xiang, Mirchev, Martin, Roychoudhury, Abhik, Shin Hwei Tan
Format:	Artikel
Sprache:	eng
Schlagworte:	Automation Fault location Language Large language models Localization Programming Repair Semantics Task complexity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!