Pruning removes 'unsafe tickets' from LLMs via gradient-free attribution, reducing harmful outputs and jailbreak vulnerability with minimal utility loss.
Understanding LLM Be- havior When Encountering User-Supplied Harmful Content in Harmless Tasks.CoRR abs/2603.11914
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
Pruning removes 'unsafe tickets' from LLMs via gradient-free attribution, reducing harmful outputs and jailbreak vulnerability with minimal utility loss.