Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset

Understand

As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified.

• Numerous guardrail models and benchmarks have been developed to ensure LLM content safety.
• However, existing guardrail benchmarks are often built upon ad hoc risk taxonomies that lack a principled grounding in standardized safety policies, limiting their alignment with real-world operational requirements.
• Moreover, they tend to overlook domain-specific risks, while the same risk category can carry different implications across different domains.