Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse user expectations. Current LLM alignment methods, however, typically provide only directional or open-ended guidance, failing to reliably achieve exact attribute intensities. We address this limitation with three key designs: (1) reformulating precise attribute intensity control as a target-reaching problem, rather than simple maximization; (2) training a lightweight value function via temporal-difference learning to predict final attribute intensity scores from partial generations, thereby steering LLM outputs; and (3) employing gradient-based interventions on hidden representations to navigate the model precisely towards specific attribute intensity targets. Our method enables fine-grained, continuous control over attribute intensities, moving beyond simple directional alignment. Experiments on LLaMA-3.2-3b and Phi-4-mini confirm our method's ability to steer text generation to user-specified attribute intensities with high accuracy. Finally, we demonstrate efficiency enhancements across three downstream tasks: preference data synthesis, Pareto frontier approximation and optimization, and distillation of aligned behaviors for intervention-free inference. Our code is available on https://github.com/Pre-Control/pre-control

翻译：精确属性强度控制——即生成具有特定用户定义属性强度的大语言模型输出——对于适应多样化用户期望的人工智能系统至关重要。然而，当前的大语言模型对齐方法通常仅提供方向性或开放式的指导，无法可靠地实现精确的属性强度。我们通过三个关键设计来解决这一局限性：(1) 将精确属性强度控制重新表述为目标达成问题，而非简单的最大化；(2) 通过时序差分学习训练一个轻量级价值函数，以从部分生成内容预测最终的属性强度分数，从而引导大语言模型输出；(3) 对隐藏表征实施基于梯度的干预，以精确引导模型朝向特定的属性强度目标。我们的方法实现了对属性强度的细粒度、连续控制，超越了简单的方向性对齐。在LLaMA-3.2-3b和Phi-4-mini上的实验证实了我们的方法能够以高准确度将文本生成引导至用户指定的属性强度。最后，我们在三个下游任务中展示了效率提升：偏好数据合成、帕累托前沿近似与优化，以及用于无干预推理的对齐行为蒸馏。我们的代码可在 https://github.com/Pre-Control/pre-control 获取。