As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety in diverse regulatory and cultural environments has become a critical challenge. However, existing multilingual benchmarks largely rely on general risk taxonomies and machine translation, which confines guardrail models to these predefined categories and hinders their ability to align with region-specific regulations and cultural nuances. To bridge these gaps, we introduce ML-Bench, a policy-grounded multilingual safety benchmark covering 14 languages. ML-Bench is constructed directly from regional regulations, where risk categories and fine-grained rules derived from jurisdiction-specific legal texts are directly used to guide the generation of multilingual safety data, enabling culturally and legally aligned evaluation across languages. Building on ML-Bench, we develop ML-Guard, a Diffusion Large Language Model (dLLM)-based guardrail model that supports multilingual safety judgment and policy-conditioned compliance assessment. ML-Guard has two variants, one 1.5B lightweight model for fast `safe/unsafe' checking and a more capable 7B model for customized compliance checking with detailed explanations. We conduct extensive experiments against 11 strong guardrail baselines across 6 existing multilingual safety benchmarks and our ML-Bench, and show that ML-Guard consistently outperforms prior methods. We hope that ML-Bench and ML-Guard can help advance the development of regulation-aware and culturally aligned multilingual guardrail systems.

翻译：随着大型语言模型（LLMs）越来越多地部署于跨语言场景中，确保其在多样化法规与文化环境下的安全性已成为一项关键挑战。然而，现有的多语言基准多依赖于通用风险分类体系与机器翻译，这限制了护栏模型仅能识别预定义的类别，阻碍其适配特定地域的法规要求与文化细微差异。为弥补这一空白，我们提出ML-Bench——一个基于策略的多语言安全基准，覆盖14种语言。ML-Bench直接基于区域法规构建，从司法管辖区特定的法律文本中提取风险类别与细粒度规则，并以此指导多语言安全数据的生成，从而实现对跨语言场景的文化与法律对齐评估。基于ML-Bench，我们开发了ML-Guard——一个基于扩散大语言模型（dLLM）的护栏模型，支持多语言安全判断与基于策略的合规性评估。ML-Guard包含两种变体：一个1.5B参数的轻量级模型用于快速执行“安全/不安全”检测，以及一个功能更强的7B模型用于定制化合规检查并提供详细解释。我们在6项现有安全基准及我们提出的ML-Bench上，与11个强护栏基线模型进行了广泛对比实验，结果表明ML-Guard在各项任务中均持续优于先前方法。我们希望ML-Bench与ML-Guard能够推动法规感知、文化对齐的多语言护栏系统的发展。