ESI framework identifies architecture-specific safety-critical parameters in LLMs, enabling SET to reduce attack success rates by over 50% via 1% weight updates and SPA to limit safety loss to under 1% during instruction tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models
ESI framework identifies architecture-specific safety-critical parameters in LLMs, enabling SET to reduce attack success rates by over 50% via 1% weight updates and SPA to limit safety loss to under 1% during instruction tuning.