Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison difficult. In this work, we present a unified view that frames these interventions as dynamic weight updates induced by a control signal, placing them within a single conceptual framework. Building on this view, we propose a unified preference-utility analysis that separates control effects into preference, defined as the tendency toward a target concept, and utility, defined as coherent and task-valid generation, and measures both on a shared log-odds scale using polarity-paired contrastive examples. Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility. We further explain this behavior through an activation manifold perspective, in which control shifts representations along target-concept directions to enhance preference, while utility declines primarily when interventions push representations off the model's valid-generation manifold. Finally, we introduce a new steering approach SPLIT guided by this analysis that improves preference while better preserving utility. Code is available at https://github.com/zjunlp/EasyEdit/blob/main/examples/SPLIT.md.

翻译：大型语言模型（LLM）的控制方法，包括局部权重微调、基于LoRA的适配以及基于激活的干预，通常被孤立研究，这掩盖了它们之间的联系并使得比较变得困难。在本工作中，我们提出一个统一视角，将这些干预框架化为由控制信号诱导的动态权重更新，并将其置于单一概念框架内。基于此视角，我们提出一种统一的偏好-效用分析，将控制效果分解为偏好（定义为朝向目标概念的倾向性）和效用（定义为连贯且任务有效的生成），并使用极性配对的对比示例在共享的对数几率尺度上度量二者。在不同方法中，我们观察到偏好与效用之间存在一致的权衡：更强的控制会增加偏好，同时可预测地降低效用。我们进一步通过激活流形视角解释此行为：控制沿目标概念方向移动表征以增强偏好，而效用下降主要发生在干预将表征推离模型的有效生成流形时。最后，我们基于此分析引入一种新的导向方法SPLIT，它在改善偏好的同时更好地保持了效用。代码可在 https://github.com/zjunlp/EasyEdit/blob/main/examples/SPLIT.md 获取。