SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia

ACL ARR 2026 January Submission1313 Authors

Keywords: AI Safety, Multilingual Safeguards, Cultural Grounding, Agentic Data Generation, Southeast Asia

Abstract: Culturally aware safeguards are crucial for AI alignment in real-world settings, where safety extends beyond common sense and encompasses diverse local values, norms, and region-specific regulations. However, building large-scale, culturally grounded datasets is challenging due to limited resources and a scarcity of native annotators. Consequently, many safeguard models rely on machine translation of English datasets, often missing regional and cultural nuances. We present a novel agentic data-generation framework to scalably create authentic, region-specific safety datasets for Southeast Asia (SEA). On this foundation, we introduce the SEA-Guard family, the first multilingual safeguard models grounded in SEA cultural contexts. Evaluated across multiple benchmarks and cultural variants, SEA-Guard consistently outperforms existing safeguards at detecting regionally sensitive or harmful content while maintaining strong general safety performance.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: Language Modeling, Multilingualism and Cross-Lingual NLP, NLP Applications

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: Burmese, Filipino, Indonesian, Malay, Tamil, Thai, Vietnamese, English

Submission Number: 1313