1
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
无需额外训练，利用kNN算法分析LLM内部激活值，实现高效且可动态配置的安全护栏，为AI防护提供新思路。
arXiv:2607.02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect uns…