Preprint
Aug 2026
BabelSteering: Multilingual Safety Alignment via English Steering Vectors
The findings suggest that activation steering may provide a practical, low- cost mechanism for extending English-derived safety signals to other languages, and introduce a multilingual translation-and-evaluation pipeline to facilitate future work on cross-lingual safety interventions.
Emma V. Stein, Dominik Meier, Terry Ruas et al.
· 0 citations