Ziyu Ge

Lost in Localization: Building RabakBench with Human-in-the-Loop Validation to Measure Multilingual Safety Gaps

2025 · arXiv (Cornell University)

Large language models (LLMs) often fail to maintain safety in low-resource language varieties, such as code-mixed vernaculars and regional dialects. We introduce RabakBench, a multilingual safety benchmark and scalable pipeline localized to Singapore's unique linguistic …