从被动到说服：局部激活注入用于共情与谈判
From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation
AI总结：
本文提出STAR方法，通过局部激活注入提升共情和谈判能力，实验证明其优于全局激活和指令预训练，表明复杂人际行为在LLM激活空间中以局部线性方向编码。
摘要：
复杂社会行为，如共情和战略礼貌，广泛被认为抵抗方向分解，这使激活引导在粗粒属性如情绪或毒性上有效。我们提出STAR：通过归因和表示引导，通过归因修补确定每个行为特征的因果起源层-标记位置，然后在这些位置注入对比激活向量。在单轮和多轮情感对话和谈判中评估，局部注入始终优于全局引导和指令预训练；人类评估证实收益反映感知质量的真实提升而非词表表面变化。我们的结果表明，复杂人际行为在LLM激活空间中编码为局部、近似线性方向，且行为对齐本质上是定位问题。
英文摘要：
Complex social behaviors, such as empathy and strategic politeness, are widely assumed to resist the directional decomposition that makes activation steering effective for coarse attributes like sentiment or toxicity. We present STAR: Steering via Attribution and Representation, which tests this assumption by using attribution patching to identify the layer--token positions where each behavioral trait causally originates, then injecting contrastive activation vectors at precisely those locations. Evaluated on emotional dialogue and negotiation in both single- and multi-turn settings, localized injection consistently outperforms global steering and instruction priming; human evaluation confirms that gains reflect genuine improvements in perceived quality rather than lexical surface change. Our results suggest that complex interpersonal behaviors are encoded as localized, approximately linear directions in LLM activation space, and that behavioral alignment is fundamentally a localization problem.
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。
