Scholar
Chen Lyu (Chen Lv)
Google Scholar ID: OZ_NVPUAAAAJ
Shandong Normal University
Citations & Impact
Citations
923
H-index
18
i10-index
27
Publications
20
Co-authors
10
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published multiple papers such as 'SemGuard: Real-Time Semantic Evaluator for Correcting LLM-Generated Code' (ASE 2025), 'Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates' (ASE 2024), and more; involved in projects like IRCoCo, KareCoder, etc.
Research Experience
- Research areas include trustworthy & efficient code generation, repo-level code security, and LLM security for code. Specific work involves high-performance, low-memory code generation, ranking generated code candidates using execution feedback, immediate rewards-guided deep reinforcement learning for code completion, etc.
Background
- Research interests lie in the intersection of intelligent software engineering and software security, with a current focus on trustworthy code generation. This includes white-box, auditable generation pipelines that embed decision & evidence into the generation process to move from explainable to auditable code. Also works on repo-level analyses and benchmarks for LLM→CodeQL generation/evaluation and LLM security for code.
Miscellany
- Open to motivated students and collaborators interested in trustworthy code generation, repo-level security, and LLM security for code.
