Latent adversarial training on 66 harm-agnostic Big-Five personality statements yields near-zero HarmBench ASR across direct requests and five jailbreaks while preserving utility.
International personality item pool: Alphabetical list of items
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Safety Alignment of Language Models via Latent Personality Traits
Latent adversarial training on 66 harm-agnostic Big-Five personality statements yields near-zero HarmBench ASR across direct requests and five jailbreaks while preserving utility.