Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection 文章

ArXiv CS.CL2026-05-28NEWSen作者: Vijeta Deshpande, Tootiya Giyahchi, Veena Padmanabhan, Leman Akoglu, Anna Rumshisky

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection · 相关技术