我们实际上能控制什么？激活控制的多行为研究
What Can We Actually Steer? A Multi-Behavior Study of Activation Control
AI总结：
本文研究了激活控制在不同行为类型中的有效性差异，发现行为类型显著影响控制效果，特征表达呈倒U型曲线，训练数据量影响控制强度。
摘要：
大型语言模型（LLMs）需要精确的行为控制以确保在各种应用中的安全和有效部署。激活控制为LLMs的行为控制提供了一种有前途的方法。我们专注于不同行为类型之间控制效果的变化以及目标行为的性质是否能预测控制成功的问题。我们通过在50种行为上进行实证分析来解决这个问题，这些行为涵盖了角色刻板印象、个性特征、不一致行为、风格线索和公众人物的模仿。我们展示了关于系数优化、向量属性和数据需求的全面实验，以提供激活控制实施的全面指导。我们的分析表明，行为类型显著影响控制效果，不同行为类别对干预强度的响应模式各不相同。我们发现特征表达遵循一个倒U型曲线，其控制系数强度。我们还表明，向量分离度量不预测控制成功，但更大的训练数据集能够实现更激进的控制。这些发现为实现激活控制提供了实证指导，并证明了控制效果严重受行为类型影响。
英文摘要：
Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how steering effectiveness varies across different behavior types and whether the nature of target behaviors can predict steering success. We address this through empirical analysis of activation steering across 50 behaviors that span persona archetypes, personality traits, misalignment behaviors, style cues, and impersonation of public figures. We present a set of comprehensive experiments on coefficient optimization, vector properties, and data requirements to provide comprehensive guidance for the implementation of activation steering. Our analysis demonstrates that steering effectiveness varies significantly by behavior type, with different behavioral categories exhibiting distinct response patterns to intervention strength. We find that trait expression follows an inverted-U curve with a steering coefficient strength. We also show that vector separation metrics do not predict steering success, but larger training datasets enable more aggressive steering. These findings provide empirically grounded guidance for implementing activation steering and demonstrate that steering effectiveness is heavily influenced by behavior type.
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。
