kNNGuard classifies prompts using multi-layer kNN on LLM hidden activations from 50 examples, matching or exceeding fine-tuned guardrails in F1 while running 2.7x to 10x faster with no training required.
arXiv preprint arXiv:2002.09247 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
kNNGuard classifies prompts using multi-layer kNN on LLM hidden activations from 50 examples, matching or exceeding fine-tuned guardrails in F1 while running 2.7x to 10x faster with no training required.