Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
This addresses safety risks in LLMs for users and regulators by providing a systematic, legally-grounded approach, though it is incremental in applying existing alignment techniques to a new benchmark.
The paper tackles the problem of ensuring LLM safety by redefining it through legal compliance frameworks like the EU AI Act and GDPR, and demonstrates that their Compliance Reasoner method improves safety performance by over 10% on these standards.
The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely on ad-hoc taxonomy and lack a rigorous, systematic protection, failing to ensure safety for the nuanced and complex behaviors of modern LLM systems. To address this problem, we solve LLM safety from legal compliance perspectives, named safety compliance. In this work, we posit relevant established legal frameworks as safety standards for defining and measuring safety compliance, including the EU AI Act and GDPR, which serve as core legal frameworks for AI safety and data security in Europe. To bridge the gap between LLM safety and legal compliance, we first develop a new benchmark for safety compliance by generating realistic LLM safety scenarios seeded with legal statutes. Subsequently, we align Qwen3-8B using Group Policy Optimization (GRPO) to construct a safety reasoner, Compliance Reasoner, which effectively aligns LLMs with legal standards to mitigate safety risks. Our comprehensive experiments demonstrate that the Compliance Reasoner achieves superior performance on the new benchmark, with average improvements of +10.45% for the EU AI Act and +11.85% for GDPR.