4 papers
From What to How: Bridging User Requirements with Software Development Using Large Language Models
Xiao He, Ru Chen, Jialun Cao
Recently, large language models (LLMs) are extensively utilized to enhance development efficiency, leading to numerous benchmarks for evaluating their performance. However, these b…
CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents
Haoyang Li, Mingjin Li, Jinxin Zuo +5
LLM-based code agents(e.g., ChatGPT Codex) are increasingly deployed as detector for code review and security auditing tasks. Although CoT-enhanced LLM vulnerability detectors are…
A Hybrid Approach for EMF Code Generation:Code Templates Meet Large Language Models
Xiao He, Ru Chen, Zeqing Zhang +2
Template-based and LLM-based code generation are both key enablers of automated software development. The former provides correctness guarantees but are rigid for complex requireme…
A Model Is Not Built By A Single Prompt: LLM-Based Domain Modeling With Question Decomposition
Ru Chen, Jingwei Shen, Xiao He
Domain modeling, a crucial part of model-driven engineering, demands extensive domain knowledge and experience from engineers. When the system description is highly complicated, th…