conftrace_

harm reduction

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

preference training (1) cultural preference (1) global harm (1) local harm (1) large language model (1) multilingual alignment (1) red teaming (1) safety alignment (1) ai safety (1) responsible ai (1)

Papers

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm EMNLP 2024