arXiv Artificial Intelligence

Local Sparsity Enables Unsupervised LLM Safety Detection

3 hours ago 18.09.2026 07:00 👁 2 views
Local Sparsity Enables Unsupervised LLM Safety Detection

Quick summary

arXiv:2609.20129v1 Announce Type: cross Abstract: 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 flagging out-of-distribution inputs. However, LLM activations lie in a high-dimensional space, raising concerns about whether anomaly detection is statist

Key takeaways

  • arXiv:2609.20129v1 Announce Type: cross Abstract: 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 flagging out-of-distribution inputs.

Why it matters

“Local Sparsity Enables Unsupervised LLM Safety Detection” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗