cs.AI updates on arXiv.org 22小时前
R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文探讨大型推理模型(LRM)的安全风险,提出R1-Act方法通过结构化推理过程激活安全知识,提升模型安全性,同时保持推理性能。

arXiv:2508.00324v1 Announce Type: new Abstract: Although large reasoning models (LRMs) have demonstrated impressive capabilities on complex tasks, recent studies reveal that these models frequently fulfill harmful user instructions, raising significant safety concerns. In this paper, we investigate the underlying cause of LRM safety risks and find that models already possess sufficient safety knowledge but fail to activate it during reasoning. Based on this insight, we propose R1-Act, a simple and efficient post-training method that explicitly triggers safety knowledge through a structured reasoning process. R1-Act achieves strong safety improvements while preserving reasoning performance, outperforming prior alignment methods. Notably, it requires only 1,000 training examples and 90 minutes of training on a single RTX A6000 GPU. Extensive experiments across multiple LRM backbones and sizes demonstrate the robustness, scalability, and practical efficiency of our approach.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

大型推理模型 安全风险 R1-Act方法
相关文章