Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
For researchers and practitioners in LLM personalization, this work provides a novel hierarchical modeling approach that improves performance and interpretability over flat behavioral methods.
This paper introduces PHF, a sociologically grounded framework for LLM personalization that models user behaviors at three hierarchical levels (practices, habitus, fields). The PHF_Compass implementation achieves consistent improvements on the LaMP benchmark across diverse tasks.
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.