作者位次 #7/9ACL 2026Poster· Natural Language Processing
Red Teaming Large Reasoning Models
Jiawei Chen · Yang Yang · Chao Yu · Yu Tian · Zhi Cao · Xue Yang · Linghao Li · Hang Su · Zhaoxia Yin
摘要
Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel safety and reliability risks, such as CoT-hijacking and prompt...