Computer Science

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?

C. Fang, N. Miao, et al.

This paper delivers a comprehensive evaluation of large language models (LLMs) for code analysis, including the challenging case of obfuscated code, and presents real-world case studies. Findings indicate LLMs can assist in automating code analysis while exhibiting certain limitations. Research conducted by Chongzhou Fang, Ning Miao, Shaurya Srivastav, Jialin Liu, Ruoyu Zhang, Ruijie Fang, Asmita, Ryan Tsang, Najmeh Nazari, Han Wang, and Houman Homayoun.