Awesome RL with Human Feedback / 2026 / arXiv

ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning

作者：Zhengyue Zhao, YingziYingzi Ma, Somesh Jha, Marco Pavone, Patrick McDaniel, Chaowei Xiao · 单位：University of Wisconsin-Madison, Stanford University · 来源：arXiv · 发布日期：2025-07-14

安全对齐对齐目标设计
新标签打开 AlphaXiv
ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning figure
AlphaXiv 中文概览（可滚动查看）