Generative Modeling of Individual Behavior at Scale

2025-02-20

AI Summary

Existing AI models predominantly capture aggregate behavioral patterns, whereas individual-level behavioral modeling faces dual challenges of poor scalability and limited generative capability. This paper introduces the first generative framework explicitly designed for individual behavior modeling. It formulates behavioral style identification as a multi-task learning problem and proposes learnable, interpretable generative style vectors that enable semantic-space manipulation and algorithmic style guidance. Coupled with parameter-efficient fine-tuning (PEFT), the framework achieves lightweight adaptation across million-scale user populations. We validate our approach across three diverse domains: chess (47K players), Rocket League (2K players), and celebrity image generation (10.1K subjects). Results demonstrate significant improvements in fidelity, controllability, and interpretability of individualized behavioral generation, establishing a foundation for scalable, expressive, and human-understandable personalization in behavioral AI.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

There has been a growing interest in using AI to model human behavior, particularly in domains where humans interact with this technology. While most existing work models human behavior at an aggregate level, our goal is to model behavior at the individual level. Recent approaches to behavioral stylometry -- or the task of identifying a person from their actions alone -- have shown promise in domains like chess, but these approaches are either not scalable (e.g., fine-tune a separate model for each person) or not generative, in that they cannot generate actions. We address these limitations by framing behavioral stylometry as a multi-task learning problem -- where each task represents a distinct person -- and use parameter-efficient fine-tuning (PEFT) methods to learn an explicit style vector for each person. Style vectors are generative: they selectively activate shared"skill"parameters to generate actions in the style of each person. They also induce a latent space that we can interpret and manipulate algorithmically. In particular, we develop a general technique for style steering that allows us to steer a player's style vector towards a desired property. We apply our approach to two very different games, at unprecedented scales: chess (47,864 players) and Rocket League (2,000 players). We also show generality beyond gaming by applying our method to image generation, where we learn style vectors for 10,177 celebrities and use these vectors to steer their images.

Problem

• Model individual human behavior
• Scalable behavioral stylometry
• Generative style vectors customization

Innovation

• Multi-task learning for individual behavior
• Parameter-efficient fine-tuning methods
• Generative style vector manipulation