# CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications

arXiv: https://arxiv.org/abs/2508.01710 · HTML: https://mlsanity.com/paper/2508.01710/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (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)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages](https://mlsanity.com/paper/2504.04377/) (2025)
- [RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?](https://mlsanity.com/paper/2404.14397/) (2024)
- [A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy](https://mlsanity.com/paper/2501.09431/) (2025)
- [Enhancing LLM Safety Through a Theoretical Minimax Game Lens](https://mlsanity.com/paper/2502.05163/) (2025)
- [STAND-Guard: A Small Task-Adaptive Content Moderation Model](https://mlsanity.com/paper/2411.05214/) (2024)
- [OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities](https://mlsanity.com/paper/2505.23856/) (2025)
- [Aligning Large Language Models to Low-Resource Languages through LLM-Based Selective Translation: A Systematic Study](https://mlsanity.com/paper/2507.14304/) (2025)

## Built on by (most cited first, 27 of 27)

- [DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection](https://mlsanity.com/paper/2607.19829/) (2026)
- [UbuntuGuard: A Culturally-Grounded Policy Benchmark for Equitable AI Safety in African Languages](https://mlsanity.com/paper/2601.12696/) (2026)
- [Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation](https://mlsanity.com/paper/2605.14404/) (2026)
- [Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators](https://mlsanity.com/paper/2606.07874/) (2026)
- [SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia](https://mlsanity.com/paper/2602.01618/) (2026)
- [Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation](https://mlsanity.com/paper/2605.28830/) (2026)
- [FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions](https://mlsanity.com/paper/2605.29427/) (2026)
- [SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification](https://mlsanity.com/paper/2607.13081/) (2026)
- [TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts](https://mlsanity.com/paper/2604.16542/) (2026)
- [BabelSafe: A Policy-Grounded Multilingual Safety Benchmark for LLMs](https://mlsanity.com/paper/2605.00689/) (2026)
- [Shieldstral](https://mlsanity.com/paper/2607.25857/) (2026)
- [The Illusion of Cross-Lingual Safety in Low-Resource Languages](https://mlsanity.com/paper/2608.11146/) (2026)
- [Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms](https://mlsanity.com/paper/2608.22335/) (2026)
- [AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models](https://mlsanity.com/paper/2603.08275/) (2026)
- [Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models](https://mlsanity.com/paper/2604.08881/) (2026)
- [ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety](https://mlsanity.com/paper/2605.14152/) (2026)
- [IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages](https://mlsanity.com/paper/2606.22841/) (2026)
- [One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs](https://mlsanity.com/paper/2607.27917/) (2026)
- [Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways](https://mlsanity.com/paper/2608.09095/) (2026)
- [Language-Specific Gaps in AI Safety Training Datasets](https://mlsanity.com/paper/2608.13695/) (2026)
- [LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2608.14626/) (2026)
- [BanglaVeilGuard: Cross-Script Safety Benchmarking and Lightweight Guardrails for Bangla Large Language Models](https://mlsanity.com/paper/2608.21880/) (2026)
- [Speculative Probing: LLM Monitoring at Speculative-Decoding Cost](https://mlsanity.com/paper/2608.28099/) (2026)
- [Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs](https://mlsanity.com/paper/2609.22144/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)
- [FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing](https://mlsanity.com/paper/2609.25298/) (2026)
- [Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails](https://mlsanity.com/paper/2609.33634/) (2026)

## Abstract (arXiv)

The increasing use of Large Language Models (LLMs) in agentic applications highlights the need for robust safety guard models. While content safety in English is well-studied, non-English languages lack similar advancements due to the high cost of collecting culturally aligned labeled datasets. We present CultureGuard, a novel solution for curating culturally aligned, high-quality safety datasets across multiple languages. Our approach introduces a four-stage synthetic data generation and filtering pipeline: cultural data segregation, cultural data adaptation, machine translation, and quality filtering. This pipeline enables the conversion and expansion of the Nemotron-Content-Safety-Dataset-V2 English safety dataset into eight distinct languages: Arabic, German, Spanish, French, Hindi, Japanese, Thai, and Chinese. The resulting dataset, Nemotron-Safety-Guard-Dataset-v3, comprises 386,661 samples in 9 languages and facilitates the training of Llama-3.1-Nemotron-Safety-Guard-8B-v3 via LoRA-based fine-tuning. The final model achieves state-of-the-art performance on several multilingual content safety benchmarks. Furthermore, we show our moderately multilingual fine-tuning enables robust cross-lingual transfer and strong zero-shot generalization to unseen languages. We also benchmark the latest open LLMs on multilingual safety and observe that these LLMs are more prone to give unsafe responses when prompted in non-English languages. This work advances multilingual LLM safety by enabling the development of culturally aware safety guard models.