SAP locates safety-correlated directions via contrastive signals and perturbs hidden-state propagation with a lightweight probe to preserve safety while fine-tuning LLMs for task performance.
Efficient sharpness-aware minimization for improved training of neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.
citing papers explorer
-
Secure LLM Fine-Tuning via Safety-Aware Probing
SAP locates safety-correlated directions via contrastive signals and perturbs hidden-state propagation with a lightweight probe to preserve safety while fine-tuning LLMs for task performance.
-
A Faster Path to Continual Learning
C-Flat Turbo accelerates continual learning by skipping redundant flatness gradients via direction-invariance observations and linear adaptive scheduling, delivering 1-1.25x speedup with comparable accuracy.