Poster · Atlanta
Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
- When
- Thu 10 Dec 2026, 10:00–13:00 EST
- Where
- Hall C1, Georgia World Congress Center
- Session
- Atlanta Poster Session 3
- Authors
- Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan, Alexander Kotov, Dongxiao Zhu
- Organisations
- Wayne State University
- QRS classification
- Language models, Safety, fairness and privacy