Study audits safety side effects of preventative persona steering in language models
A new arXiv paper presents an empirical audit of preventative persona steering, examining how activation-space directions linked to behaviors like sycophancy and hallucination affect model safety.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-16 05:00 · arXiv cs.AI
Safety Side Effects of Preventative Persona Steering: An Empirical Audit