# SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures

arXiv: https://arxiv.org/abs/2512.05501 · HTML: https://mlsanity.com/paper/2512.05501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://mlsanity.com/paper/2501.09004/) (2025)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages](https://mlsanity.com/paper/2406.10118/) (2024)
- [WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines](https://mlsanity.com/paper/2410.12705/) (2024)
- [Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration](https://mlsanity.com/paper/2410.15644/) (2024)
- [SoK: Evaluating Jailbreak Guardrails for Large Language Models](https://mlsanity.com/paper/2506.10597/) (2025)
- [MPO: Multilingual Safety Alignment via Reward Gap Optimization](https://mlsanity.com/paper/2505.16869/) (2025)
- [Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu](https://mlsanity.com/paper/2502.11862/) (2025)
- [X-Guard: Multilingual Guard Agent for Content Moderation](https://mlsanity.com/paper/2504.08848/) (2025)
- [A Statistical Framework for Ranking LLM-Based Chatbots](https://mlsanity.com/paper/2412.18407/) (2024)
- [SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore](https://mlsanity.com/paper/2405.01842/) (2024)
- [LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators](https://mlsanity.com/paper/2507.15339/) (2025)
- [Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service](https://mlsanity.com/paper/2411.12262/) (2024)
- [SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems](https://mlsanity.com/paper/2507.08898/) (2025)

## Abstract (arXiv)

Safeguard models help large language models (LLMs) detect and block harmful content, but most evaluations remain English-centric and overlook linguistic and cultural diversity. Existing multilingual safety benchmarks often rely on machine-translated English data, which fails to capture nuances in low-resource languages. Southeast Asian (SEA) languages are underrepresented despite the region's linguistic diversity and unique safety concerns, from culturally sensitive political speech to region-specific misinformation. Addressing these gaps requires benchmarks that are natively authored to reflect local norms and harm scenarios. We introduce SEA-SafeguardBench, the first human-verified safety benchmark for SEA, covering eight languages, 21,640 samples, across three subsets: general, in-the-wild, and content generation. The experimental results from our benchmark demonstrate that even state-of-the-art LLMs and guardrails are challenged by SEA cultural and harm scenarios and underperform when compared to English texts.