DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

2025-02-16

AI Summary

To address the challenges of sustaining persona model optimization and limited behavioral prediction accuracy in dynamic real-world scenarios, this paper proposes an iterative reinforcement learning (RL)-based targeted refinement framework. Methodologically, it introduces a novel direction-search-enhanced RL paradigm that automatically identifies effective update pathways by modeling behavior-prediction discrepancies, enabling interpretable, bias-driven persona evolution. Furthermore, it integrates large language models (LLMs) to construct fine-grained, temporally aware persona representations and adaptive update mechanisms. Experimental evaluation across 10 domains involving 4,800 users demonstrates that, after four iterative refinement rounds, the framework reduces average behavioral prediction error by 32.2%, outperforming the best baseline by 22.92%. This work advances persona modeling through explainable, discrepancy-guided adaptation and LLM-powered temporal representation learning.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Learning to Search

Application Category

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

Abstract

To advance personalized applications such as recommendation systems and user behavior prediction, recent research increasingly adopts large language models (LLMs) for human -readable persona modeling. In dynamic real -world scenarios, effective persona modeling necessitates leveraging streaming behavior data to continually optimize user personas. However, existing methods -whether regenerating personas or incrementally extending them with new behaviors -often fail to achieve sustained improvements in persona quality or future behavior prediction accuracy. To address this, we propose DEEPER, a novel approach for dynamic persona modeling that enables continual persona optimization. Specifically, we enhance the model's direction -search capability through an iterative reinforcement learning framework, allowing it to automatically identify effective update directions and optimize personas using discrepancies between user behaviors and model predictions. Extensive experiments on dynamic persona modeling involving 4800 users across 10 domains highlight the superior persona optimization capabilities of DEEPER, delivering an impressive 32.2% average reduction in user behavior prediction error over four update rounds -outperforming the best baseline by a remarkable 22.92%.

Problem

• Enhance dynamic persona modeling accuracy.
• Optimize user personas using behavior data.
• Reduce prediction error in user behavior.

Innovation

• Dynamic persona modeling
• Iterative reinforcement learning
• Behavior prediction optimization