Author name: Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci

arXiv:2603.24543v1 Announce Type: cross
Abstract: Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implicatio…