Similar Items: Prompt engineering in LLMs for automated unit test generation: A large-scale study
- Robustness evaluation and enhancement of LLMs in code generation: an empirical study
- Automated machine learning for test case prioritisation
- A large-scale empirical study of configurations, errors, and warnings for compilation in continuous integration
- Do code LLMs do static analysis?
- ArkTS code generation: A comprehensive evaluation with large language models
- Cracking IoT security: can LLMs outsmart static analysis tools?