Evaluating the Role of Context Representations in the Behavioral Fidelity of LLM-based Personas for Food Preferences

Recent work has increasingly relied on LLM-based personas to reason about food preferences, yet the information used to condition these personas is often unstructured, inconsistently represented, or weakly validated. This observation naturally leads to ask whether, and to what extent, LLM-based personas respond to more structured user context representations inspired by those typically adopted in nutritional practice. In this paper, we hence study the role of context representations in the food domain by comparing three forms of context (unstructured, structured, and hybrid) when conditioning LLM-based personas. We evaluate behavioral fidelity by comparing simulated ratings and generated reviews against real user data. Our results show that unstructured text better preserves rating intensity, structured traits alone do not capture preferences well, and hybrid representations yield the most faithful simulations. Repository: https://github.com/tail-unica/food-digital-twin.