作者位次 #5/7ACL 2026Findings· Findings of ACL
SAFER : Advancing Safety Alignment via Efficient Ex-Ante Reasoning
Kehua Feng · Keyan Ding · Yuhao Wang · Menghan Li · Fanjunduo Wei · Xinda Wang · Huajun Chen
摘要
Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often struggle to cover diverse safety scenarios and remain vulnerable...