What You See Is Not Always What You Get: An Empirical Study of Code Comprehension by Large Language Models

Recent studies have demonstrated outstanding capabilities of large language models (LLMs) in software engineering domain, covering numerous tasks such as code generation and comprehension. While the benefit of LLMs for coding task is well noted, it is perceived that LLMs are vulnerable to adversaria...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Zhu, Bangshuo, Wen, Jiawen, Chen, Huaming
Format:	Artikel
Sprache:	eng
Schlagworte:	Chatbots Coding Correlation Design of experiments Human performance Impact analysis Large language models Performance evaluation Perturbation
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!