作者位次 #3/22ACL 2026Findings· Findings of ACL
A . S . E : A Repository-Level Benchmark for Evaluating Security in AI -Generated Code
Keke Lian · Wang Bin · Lei Zhang · Libo Chen · Junjie Wang · Ziming Zhao · Yujiu Yang · Miaoqian Lin · Haotong Duan · Haoran Zhao · Shuang Liao · Mingda Guo · Quan Jiazheng · Yilu Zhong · Chenhao He · Chen Zichuan · Jie Wu · Haoling Li · Zhaoxuan Li · Jiongchi Yu · Hui LI · Dong Zhang
摘要
The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks often lack relevance to real-world AI-assisted programming scenarios, making them inadequate for assessing the practical...