Assigning personas to Chinese LLMs amplifies toxic output relative to default behavior, while refusal rates shift systematically with persona gender and target social group.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Assigning personas to Chinese LLMs amplifies toxic output relative to default behavior, while refusal rates shift systematically with persona gender and target social group.