task · first seen 5 Oct 2026
small language model safety
Deployment-time safety mechanisms such as moderation, routing, and output filtering for small language models.
Mentions per week
PapersCodeDiscussion
Earliest sources
- SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language ModelsPapers · 5 Oct 2026 · Xingru Zhou, Luis Sentis, Aarti Choudhary
Latest sources
- SAFESHIELD: A Decision-Organization Framework for Deployment-Time Safety of Small Language ModelsPapers · 5 Oct 2026 · Xingru Zhou, Luis Sentis, Aarti Choudhary