AI 中文总结
本文提出LatentPersonal框架，通过共享潜在适应空间中的导航，利用少量用户样本推断紧凑表示，结合LoRA实现高效个性化，显著降低适应开销并在单样本场景中表现优异。
AI 中文摘要
大语言模型（LLMs）日益被期望适应个体用户，然而在仅有少量用户特定样本可用时，有效的个性化仍然具有挑战性。在这项工作中，我们采取了一个不同的视角：预训练的大语言模型可能已经具备个性化的潜在能力，因此，少量用户样本可能就足以引导模型朝向与用户对齐的行为，且只需极少的用户特定适应。基于这一视角，我们提出了LatentPersonal，一个将个性化表述为在共享潜在适应空间中进行导航的框架。LatentPersonal从少量用户样本中推断出一个紧凑的潜在表示，以引导用户特定的模型适应，并通过变分信息瓶颈进行正则化，以鼓励紧凑的偏好表示。我们使用LoRA实例化LatentPersonal，利用其低秩参数化作为个性化的自然低维适应空间。通过简单地在共享低秩因子之间插入一个用户特定的引导向量，模型可以通过对该紧凑表示的轻量级推断来导航至个性化适应，而无需更新共享的LoRA参数。在多个个性化数据集上的实验表明，LatentPersonal大幅减少了用户特定的适应开销，同时仅从少量用户特定交互中就能实现有效的个性化，尤其是在单样本场景中表现尤为突出。
英文摘要
Large language models (LLMs) are increasingly expected to adapt to individual users, yet effective personalization remains challenging when only limited user-specific samples are available. In this work, we take an alternative perspective: pretrained LLMs may already possess latent capacity for personalization, and a few user samples may therefore suffice to guide the model toward user-aligned behavior with minimal user-specific adaptation. From this perspective, we propose LatentPersonal, a framework that formulates personalization as navigation in a shared latent adaptation space. LatentPersonal infers a compact latent representation from a few user samples to guide user-specific model adaptation, regularized with a variational information bottleneck to encourage compact preference representations. We instantiate LatentPersonal with LoRA, leveraging its low-rank parameterization as a natural low-dimensional adaptation space for personalization. By simply inserting a user-specific guidance vector between the shared low-rank factors, the model can navigate toward personalized adaptations through lightweight inference of this compact representation, without updating the shared LoRA parameters. Experiments across multiple personalization datasets demonstrate that LatentPersonal substantially reduces user-specific adaptation overhead while achieving effective personalization from only a few user-specific interactions, with particularly strong performance in the one-shot regime.
