CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses to both harmful and benign inputs. We propose \textbf{C}ontinuous \textbf{L}at\textbf{E}nt \textbf{A}dapter \textbf{R}outing (CLEAR), a conditional safety adaptation framework that uses a lightweight hidden-state gate to continuously control the…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
