conftrace_

guardrail sensitivity

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

language model safety (1) large language model (1) ideological bia (1) user persona (1) user bia (1) political ideology (1) political bia (1) demographic bia (1) bias evaluation (1) refusal behavior (1)

Papers

ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Context EMNLP 2024