Large language models (LLMs) are being deployed across the Global South, where everyday use involves low-resource languages, code-mixing, and culturally specific norms. Yet safety pipelines, benchmarks, and alignment still largely target English and a handful of high-resource languages, implicitly assuming safety and factuality ''transfer'' across languages. Evidence increasingly shows they do not. We synthesize recent findings indicating that (i) safety guardrails weaken sharply on low-resource and code-mixed inputs, (ii) culturally harmful behavior can persist even when standard toxicity scores look acceptable, and (iii) English-only knowledge edits and safety patches often fail to carry over to low-resource languages. In response, we outline a practical agenda for researchers and students in the Global South: parameter-efficient safety steering, culturally grounded evaluation and preference data, and participatory workflows that empower local communities to define and mitigate harm. Our aim is to make multilingual safety a core requirement-not an add-on-for equitable AI in underrepresented regions.
@article{arxiv.2602.13867,
title = {Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages},
author = {Somnath Banerjee and Rima Hazra and Animesh Mukherjee},
journal= {arXiv preprint arXiv:2602.13867},
year = {2026}
}