Internal Activation as the Polar Star for Steering Unsafe LLM Behavior

원문 초록

Large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks but also pose significant risks due to their potential to generate harmful content. Although existing safety mechanisms can improve model safety, they often lead to overly cautious behavior and fail to fully utilize LLMs' internal cognitive processes. Drawing inspiration from cognitive science, where humans rely on reflective reasoning (System 2 thinking) to regulate language and behavior, we empirically demonstrate that LLMs also possess a similar capacity for internal assessment and regulation, which can be actively detected. Building on this insight, we introduce SafeSwitch, a framework that dynamically regulates unsafe outputs by monitoring and utilizing the model's internal states. Our empirical results show that SafeSwitch reduces harmful outputs by over 80% on safety benchmarks while maintaining strong utility. Compared to traditional safety alignment methods, SafeSwitch delivers more informative and context-aware refusals, demonstrates resilience to unseen queries, and achieves these benefits while only tuning less than 6% of the original parameters. These features make SafeSwitch a promising approach for implementing nuanced safety controls in LLMs.