2 papers
cs.AI2026
The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation
Diaoulé Diallo, Katharina Dworatzyk, Sophie Jentzsch +3
Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering…
cs.SE2025
Overcoming the hurdle of legal expertise: A reusable model for smartwatch privacy policies
Constantin Buschhaus, Arvid Butting, Judith Michael +5
Regulations for privacy protection aim to protect individuals from the unauthorized storage, processing, and transfer of their personal data but oftentimes fail in providing helpfu…