Multilingual jailbreaks succeed mainly by routing harm through misaligned residual subspaces that under-project onto an intact, effectively one-dimensional cross-lingual refusal direction.
SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention , url=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety
Multilingual jailbreaks succeed mainly by routing harm through misaligned residual subspaces that under-project onto an intact, effectively one-dimensional cross-lingual refusal direction.