作者位次 #2/4ACL 2026Findings· Findings of ACL
Program Structure-aware Language Models: Targeted Software Testing beyond Textual Semantics
Khang Tran · Khoa Nguyen · Cristian Borcea · Hai Phan
摘要
Recent advances in large language models for test case generation have improved branch coverage via prompt-engineered mutations. However, they still lack principled mechanisms for steering models toward specific high-risk execution branches, limiting their effectiveness for discovering subtle bug...