研究不同行为类型在激活控制下的可调节性，发现效果因行为类型而异。
What Can We Actually Steer? A Multi-Behavior Study of Activation Control
- 通过50种行为的实证分析，测试激活控制对不同行为的影响。
- 性格表达随控制强度呈倒U型变化，存在最优干预点。
- 向量分离度无法预测控制效果，但数据量大则可更强干预。
大型语言模型（LLMs）在多样应用中需精确的行为控制以确保安全与有效。激活控制为实现这一目标提供了有前景的途径。本文聚焦于控制效果如何随行为类型变化，以及目标行为的性质能否预测控制成功。通过针对50种行为的实证分析，涵盖人格原型、性格特质、偏差行为、风格线索及公众人物模仿等类别，系统评估了系数优化、向量属性和数据需求。结果表明，控制效果显著依赖于行为类型，不同类别对干预强度响应模式各异。性格表达随控制系数呈现倒U型曲线关系。向量分离度指标无法预测控制成效，但更大的训练数据集支持更激进的控制策略。这些发现为激活控制的实践提供基于实证的指导，并揭示控制效果高度受行为类型影响。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。