Jailbreak-induced performance loss shrinks as model capability grows, with the strongest models showing almost no degradation on benchmarks.
Speak Easy: Eliciting Harmful Jailbreaks from
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
-
Jailbroken Frontier Models Retain Their Capabilities
Jailbreak-induced performance loss shrinks as model capability grows, with the strongest models showing almost no degradation on benchmarks.