AINeutralarXiv – CS AI · 6h ago7/10
🧠
Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
Researchers discovered that key-value cache quantization—a technique used to reduce LLM inference memory—silently degrades AI safety alignment without affecting standard performance metrics like perplexity. The study identifies the root cause as geometric vulnerability of safety features in low-dimensional activation subspaces and proposes Per-Channel Reduction (PCR), a diagnostic tool that achieves up to 97% alignment recovery without retraining.
🏢 Nvidia🏢 Perplexity