Second-order screen predicts quantization mismatch on five language models
On unseen Mistral-7B-v0.3, all six predictions fell in band and vLLM throughput was predicted within 0.4%.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #fisher-information
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
FDCU uses dual-constrained projection to erase hazardous LLM knowledge and resist retraining attacks that revive unlearned behavior.