AAAI

AAAI Conference on Artificial Intelligence · 会议 · Artificial Intelligence

2026-02-17 至 2026-02-17 共收录 1 篇

2602.13867 2026-02-17 cs.CL

Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages

弥合多语言安全鸿沟：为全球南方语言实现高效、文化感知的对齐

Somnath Banerjee, Rima Hazra, Animesh Mukherjee

AI总结本文提出为全球南方低资源语言提供高效、文化感知的安全对齐方法，以解决现有安全机制在多语言环境中的失效问题。

Comments Accepted to the EGSAI Workshop at AAAI 2026

↑