SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918318653308928 |
|---|---|
| author | Tasawong, Panuthep Ngui, Jian Gang Aji, Alham Fikri Cohn, Trevor Limkonchotiwat, Peerat |
| author_facet | Tasawong, Panuthep Ngui, Jian Gang Aji, Alham Fikri Cohn, Trevor Limkonchotiwat, Peerat |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01618 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia Tasawong, Panuthep Ngui, Jian Gang Aji, Alham Fikri Cohn, Trevor Limkonchotiwat, Peerat Computation and Language 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. |
| title | SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.01618 |