TRIPLE: Theory-Driven Integration of Planned and Habitual Behaviors for LLM-based Personalization

While large language model (LLM)-based user profiling of- fers significant potential for personalization, most existing approaches rely on empirical heuristics and lack grounding in the psychological mechanism that drive human behavior. In this paper, we introduce TRIPLE (Theory-guided Rea- soning for Intent and habIt Profiling with LLMs for pEr- sonalization), a novel framework that systematically inte- grates dual-process theory from social psychology into LLM- based user modeling. TRIPLE (1) constructs a habitual be- havior profile by identifying repeated patterns over time to model automatic responses; (2) builds an intentional behav- ior profile by inferring user attitudes, subjective norms and perceived behavioral control based on the Theory of Planned Behavior (TPB); and (3) generates behavioral rationale that reveal the interaction between habitual and intentional pro- cesses to predict user behavior in context-specific situations. We evaluate TRIPLE on five personalization tasks from the LaMP benchmark using multiple open-source LLMs. Re- sults show that TRIPLE consistently outperforms existing in- context learning methods, with especially pronounced gains on complex generative tasks such as headline and title gen- eration.Qualitative analyses further demonstrate that the pro- files and reasoning paths generated by TRIPLE provide inter- pretable and psychologically grounded explanations of user behavior. These findings provide strong evidence that incor- porating validated behavioral theories into LLM-based per- sonalization enhances both predictive performance and inter- pretability, paving a way for theory-driven, socio-cognitively informed user modeling.