Local Sparsity Enables Unsupervised LLM Safety Detection
Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks and harm categories regularly arise, not captured by models trained in such a supervised fashion. An alternative approach is to view this problem through the lens of anomaly detection, namely, to rely solely on modeling safe data and…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
