A Systematic Survey on Large Language Models for Static Code Analysis

code analysis plays a pivotal role in improving software quality, security, and maintainability by detecting vulnerabilities, errors, and programming issues in source code without executing it. Recent advancements in artificial intelligence, especially the development of large language models (LLMs), such as ChatGPT, have enabled transformational opportunities in this domain. Thus, it is essential to explore this emerging field of research from many perspectives. This systematic survey focuses on the use of LLMs for static code analysis, detailing their applications, advantages, contexts, limitations, etc. The study examines research papers published on the topic from reputable literature databases to answer several research questions regarding the state-of-the-art use of LLMs in static code analysis. In addition, different research gaps and challenges were identified and discussed alongside many directions. The results of this study demonstrate how LLMs can enhance static code analysis and address existing limitations, paving the way for developers and researchers to employ LLMs for a more affordable and effective software development process.