#Prompt safety
Latest news articles tagged with "Prompt safety". Follow the timeline of events, related topics, and entities.
Articles (1)
-
🇺🇸 A Lightweight Explainable Guardrail for Prompt Safety
[USA]
arXiv:2602.15853v1 Announce Type: cross Abstract: We propose a lightweight explainable guardrail (LEG) method for the classification of unsafe prompts. LEG uses a multi-task learning architecture to ...
Related: #AI safety, #Explainable AI, #Multi‑task learning, #Synthetic data generation