Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
Paper recorded by Signals 4 on 2026-09-22 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-22 on arXiv · recorded by Signals 4 on 2026-09-23
Category: cs.AI · 人工智能 · first seen 2026-09-23
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 scientifically unreliable metric for single-function vulnerability repair, and we support this with five controlled experiments over 203 vulnerable functions
Read on arXiv →
Cite this page: Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen: the #8 most recent of 360 cs.AI papers we have recorded (as of 2026-09-22). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/metrics-failure-in-llm-based-code-vulnerability-repair-an-empirical-study-and-a-.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free