超越静态对齐：基于风险感知链条思维的 LLM 安全层次化策略控制

大型语言模型 (LLM) 因静态单一化的安全策略缺乏运行时可控性而面临根本性的安全-有用性权衡，难以为不同应用场景定制响应。%结果，模型可能过度拒绝善意请求或对有害请求保护不足。我们提出 PACT (Prompt-configured Action via Chain-of-Thought)，一种通过显式风险感知推理实现动态安全控制的框架。PACT operates in a hierarchical policy architecture: a non-overridable global safety policy establishes immutable boundaries for critical risks (e.g., child safety, violent extremism), while user-defined policies can introduce domain-specific (non-global) risk categories and specify label-to-action behaviors to improve utility in real-world deployment settings. The framework decomposes safety decisions into structured Classify→Act paths that route queries to the appropriate action (comply, guide, or reject) and render the decision-making process transparent. Extensive experiments demonstrate that PACT achieves near state-of-the-art safety performance under global policy evaluation while attaining the best controllability under user-specific policy evaluation, effectively mitigating the safety-helpfulness trade-off. We will release the PACT model suite, training data, and evaluation protocols to facilitate reproducible research in controllable safety alignment.