面向代码的大语言模型的鲁棒性、安全性、隐私性、可解释性、效率与可用性
Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code
AI总结:
本文针对当前缺乏面向代码的大语言模型非功能属性系统综述的空白,通过调研146项相关研究,首次系统梳理了该模型准确率之外的鲁棒性等多项重要属性的研究现状、前沿方法与趋势,并提出未来研究方向。
摘要:
面向代码的大语言模型(LLM4Code)在处理源代码方面表现出强劲性能(如高准确率),已显著变革了软件工程领域。现有诸多研究分别探究LLM4Code的非功能属性,但尚无针对这些属性如何被评估与增强的系统性综述。本文通过全面调研146项相关研究填补了这一空白,开展了首项系统性文献综述,识别出准确率之外的7项重要属性,包括鲁棒性、安全性、隐私性、可解释性、效率与可用性。我们讨论了当前的前沿方法与发展趋势,指出现有研究的空白,并提出了未来研究的可行方向。
英文摘要:
Large language models for code (LLM4Code), which demonstrate strong performance (e.g., high accuracy) in processing source code, have significantly transformed software engineering. Many studies separately investigate the non-functional properties of LM4Code, but there is no systematic review of how these properties are evaluated and enhanced. This paper fills this gap by thoroughly examining 146 relevant studies, thereby presenting the first systematic literature review to identify seven important properties beyond accuracy, including robustness, security, privacy, explainability, efficiency, and usability. We discuss the current state-of-the-art methods and trends, identify gaps in existing research, and present promising directions for future study.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。