Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning

TL;DR

This paper introduces ATHENA, a novel framework combining utility optimization and textual reasoning with LLMs to personalize decision models, significantly improving prediction accuracy in high-stakes individual choices.

Contribution

ATHENA uniquely integrates symbolic utility discovery with semantic adaptation using LLMs, advancing personalized decision modeling beyond existing utility-based and machine learning approaches.

Findings

ATHENA outperforms existing models with at least 6.5% higher F1 score.

Both stages of ATHENA are essential for optimal performance.

The framework effectively models individual decision-making in real-world tasks.

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.