Safety alignment in LLMs is not uniform but forms a demographic hierarchy, with defense rates varying by up to 42% across groups; a new benchmark and DPO method demonstrate transferable safety.
intent_analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
Safety alignment in LLMs is not uniform but forms a demographic hierarchy, with defense rates varying by up to 42% across groups; a new benchmark and DPO method demonstrate transferable safety.