X-Guard：用于内容审核的多语言防护智能体
X-Guard: Multilingual Guard Agent for Content Moderation
AI总结：
针对现有LLM安全防护在多语言场景下的漏洞，本文提出透明多语言防护智能体X-Guard，通过构建跨语言数据集、采用评委团方法及两阶段架构，有效防御低资源语言对抗攻击与代码切换攻击，提升决策透明度。
摘要：
大型语言模型（LLMs）已迅速成为众多关键领域应用的核心，这些领域对可靠性要求极高。尽管安全框架和防护措施取得了显著进展，但当前保护措施仍存在关键漏洞，尤其是在多语言环境中。现有安全系统在低资源语言和代码切换技术下易受对抗攻击，主要因其以英语为中心的设计。此外，多样化跨语言训练数据的稀缺限制了有效多语言防护措施的开发。即使是Llama Guard-3等近期解决方案，虽提供多语言支持，但其决策过程缺乏透明度。我们通过引入X-Guard智能体解决这些挑战，它是一个透明的多语言安全智能体，旨在跨不同语言环境提供内容审核。X-Guard能有效防御传统低资源语言攻击和复杂代码切换攻击。我们的方法包括：整理并增强多个带明确评估理由的开源安全数据集；采用评委团方法减轻单个评委LLM提供商的偏见；创建涵盖132种语言、含500万数据点的综合多语言安全数据集；开发两阶段架构，结合自定义微调的mBART-50翻译模块与通过监督微调及GRPO训练的评估型X-Guard 3B模型。实证评估表明，X-Guard在多语言环境中检测不安全内容的有效性，同时在整个安全评估过程中保持透明度。我们的工作为LLMs及其集成系统构建稳健、透明且语言包容的安全系统迈出了重要一步。
英文摘要：
Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety frameworks and guardrails, current protective measures exhibit crucial vulnerabilities, particularly in multilingual contexts. Existing safety systems remain susceptible to adversarial attacks in low-resource languages and through code-switching techniques, primarily due to their English-centric design. Furthermore, the development of effective multilingual guardrails is constrained by the scarcity of diverse cross-lingual training data. Even recent solutions like Llama Guard-3, while offering multilingual support, lack transparency in their decision-making processes. We address these challenges by introducing X-Guard agent, a transparent multilingual safety agent designed to provide content moderation across diverse linguistic contexts. X-Guard effectively defends against both conventional low-resource language attacks and sophisticated code-switching attacks. Our approach includes: curating and enhancing multiple open-source safety datasets with explicit evaluation rationales; employing a jury of judges methodology to mitigate individual judge LLM provider biases; creating a comprehensive multilingual safety dataset spanning 132 languages with 5 million data points; and developing a two-stage architecture combining a custom-finetuned mBART-50 translation module with an evaluation X-Guard 3B model trained through supervised finetuning and GRPO training. Our empirical evaluations demonstrate X-Guard's effectiveness in detecting unsafe content across multiple languages while maintaining transparency throughout the safety evaluation process. Our work represents a significant advancement in creating robust, transparent, and linguistically inclusive safety systems for LLMs and its integrated systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
