超越孤立行为：面向LLM个性化的层次化用户建模
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
AI总结：
针对LLM个性化中用户行为缺乏层次结构的问题，提出基于布迪厄实践理论的PHF框架，通过实践-惯习-场域三层建模，并实现轻量级模型无关方法PHF_Compass，在LaMP基准上取得一致提升。
摘要：
大型语言模型（LLM）在多个领域展现出卓越能力，但将其输出个性化以适应个体用户仍是一个开放挑战。现有方法主要采用扁平行为范式，聚合用户行为而未明确考虑它们如何组织成更深层的行为结构。在本工作中，我们借鉴皮埃尔·布迪厄的实践理论，提出PHF（实践-惯习-场域），一个基于社会学的框架，通过三个层次重新概念化LLM个性化：作为实践的个人行为、作为惯习的行为在时间上的积累形成稳定倾向、以及作为场域的相似用户间的共享规律。我们通过$\mathrm{PHF}_{ ext{Compass}}$实例化PHF，这是一种基于冻结LLM的轻量级且模型无关的实现。在语言模型个性化（LaMP）基准上的实验表明，该方法在多种任务上取得一致改进，进一步分析验证了所学行为结构的可解释性和可扩展性。
英文摘要：
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, yet personalizing their outputs to individual users remains an open challenge. Existing approaches predominantly adopt a flat behavioral paradigm, aggregating user behaviors without an explicit account of how they are organized into deeper behavioral structures. In this work, we draw on Pierre Bourdieu's Theory of Practice to propose PHF (Practice-Habitus-Field), a sociologically grounded framework that reconceptualizes LLM personalization through three hierarchical levels: individual behaviors as practices, their temporal accumulation into stable dispositions as habitus, and shared regularities across similar users as fields. We instantiate PHF through $\mathrm{PHF}_{\text{Compass}}$, a lightweight and model-agnostic implementation based on a frozen LLM. Experiments on the Language Model Personalization (LaMP) benchmark demonstrate consistent improvements across diverse tasks, while further analyses validate the interpretability and extensibility of the learned behavioral structures.
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。
