NeuronTune identifies sparse safety and utility neurons via attack-aware attribution, optimizes per-neuron scaling factors with MAML, and reports a better safety-utility balance than layer-wise alignment methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
NeuronTune identifies sparse safety and utility neurons via attack-aware attribution, optimizes per-neuron scaling factors with MAML, and reports a better safety-utility balance than layer-wise alignment methods.