AI RESEARCH
RESCUE: Retrieval Augmented Secure Code Generation
arXiv CS.LG
•
ArXi:2510.18204v2 Announce Type: replace-cross Despite recent advances, Large Language Models (LLMs) still generate vulnerable code. Retrieval-Augmented Generation (RAG) has the potential to enhance LLMs for secure code generation by incorporating external security knowledge. However, the conventional RAG design struggles with the noise of raw security-related documents, and existing retrieval methods overlook the significant security semantics implicitly embedded in task descriptions.