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：控制大型语言模型（LLMs）的方法，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，我们提出了一个统一视角，将这些干预框架化为由控制信号诱导的动态权重更新，并将其置于一个单一的概念框架内。基于此视角，我们提出了一种统一的偏好-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对两者进行度量。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这种行为：控制沿着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了一种新的导向方法SPLIT，它在改善偏好的同时更好地保留了效用。代码可在 https://github.com/zjunlp/EasyEdit/blob/main/examples/SPLIT.md 获取。