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.
Interpretability in Activation Space Analysis of Transformers: A Focused Survey , shorttitle =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
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.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.