Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.26749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to the automated repair of C/C++ security vulnerabilities, and compile rate is a commonly reported proxy for progress: whether the generated patch compiles. We argue that compile rate is a…

aisciencesecurity

Sources

• T1Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware ScreenarXiv24 Sept, 04:00