Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning

2025-11-04

AI Summary

In high-stakes personalized decision-making (e.g., vaccination), individual choices frequently deviate from population-optimal predictions due to unmodeled interactions between numerical attributes (e.g., cost, time) and linguistic factors (e.g., preferences, constraints). To address this, we propose ATHENA—a novel framework that synergistically integrates large language models’ (LLMs) textual reasoning capabilities with utility theory, enabling a symbolic–semantic, two-stage adaptive modeling process: first, LLM-driven symbolic utility discovery; second, individualized adjustment via personalized semantic templates. ATHENA jointly captures population-level regularities and individual-level heterogeneity while explicating the interplay between numerical and linguistic determinants. Evaluated on real-world travel and vaccination decision tasks, ATHENA achieves ≥6.5% absolute F1-score improvement over the strongest baseline, demonstrating both effectiveness and robustness.

Technology Category

• Reasoning under Uncertainty: Decision/Utility Theory
• Humans and AI: Learning Human Values and Preferences
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Decision-making models for individuals, particularly in high-stakes scenarios like vaccine uptake, often diverge from population optimal predictions. This gap arises from the uniqueness of the individual decision-making process, shaped by numerical attributes (e.g., cost, time) and linguistic influences (e.g., personal preferences and constraints). Developing upon Utility Theory and leveraging the textual-reasoning capabilities of Large Language Models (LLMs), this paper proposes an Adaptive Textual-symbolic Human-centric Reasoning framework (ATHENA) to address the optimal information integration. ATHENA uniquely integrates two stages: First, it discovers robust, group-level symbolic utility functions via LLM-augmented symbolic discovery; Second, it implements individual-level semantic adaptation, creating personalized semantic templates guided by the optimal utility to model personalized choices. Validated on real-world travel mode and vaccine choice tasks, ATHENA consistently outperforms utility-based, machine learning, and other LLM-based models, lifting F1 score by at least 6.5% over the strongest cutting-edge models. Further, ablation studies confirm that both stages of ATHENA are critical and complementary, as removing either clearly degrades overall predictive performance. By organically integrating symbolic utility modeling and semantic adaptation, ATHENA provides a new scheme for modeling human-centric decisions. The project page can be found at https://yibozh.github.io/Athena.

Problem

• Individual decision models diverge from population optimal predictions in high-stakes scenarios
• Personalized decisions combine numerical attributes with linguistic preferences and constraints
• Optimal information integration requires bridging utility optimization and symbolic reasoning

Innovation

• LLM-augmented symbolic discovery for utility functions
• Individual-level semantic adaptation using personalized templates
• Integrates symbolic utility modeling with semantic adaptation