To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models

16 February 2025

Papers citing "To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models"

3 / 3 papers shown

Title
Safety in Large Reasoning Models: A Survey Cheng Wang Yong Liu Yangqiu Song Duzhen Zhang ZeLin Li Junfeng Fang Bryan Hooi LRM 159 1 0 24 Apr 2025
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs Gejian Zhao Hanzhou Wu Xinpeng Zhang Athanasios V. Vasilakos LRM 38 1 0 08 Apr 2025
Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable Tiansheng Huang Sihao Hu Fatih Ilhan Selim Furkan Tekin Zachary Yahn Yichang Xu Ling Liu 53 9 0 01 Mar 2025