Be.FM: Open Foundation Models for Human Behavior

2025-05-29

AI Summary

This paper addresses the underexplored application of foundation models to human behavior modeling and understanding. We introduce Be.FM—the first open-source foundation model for human behavior. Methodologically, Be.FM builds upon open-source large language models and is fine-tuned using multi-source, heterogeneous behavioral data, integrating transfer learning, prompt engineering, and domain-specific knowledge injection from behavioral science. Our key contributions are: (1) the first open-source foundation model framework explicitly designed for human behavior modeling; (2) the first comprehensive benchmark suite for evaluating behavioral foundation models; and (3) support for cross-scenario, interpretable behavior prediction, individual- and population-level trait inference, and context-driven insight generation. Experiments demonstrate that Be.FM significantly outperforms existing baselines across diverse behavioral prediction and inference tasks, while enabling fine-grained decision simulation and demographic attribute reconstruction.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Despite their success in numerous fields, the potential of foundation models for modeling and understanding human behavior remains largely unexplored. We introduce Be.FM, one of the first open foundation models designed for human behavior modeling. Built upon open-source large language models and fine-tuned on a diverse range of behavioral data, Be.FM can be used to understand and predict human decision-making. We construct a comprehensive set of benchmark tasks for testing the capabilities of behavioral foundation models. Our results demonstrate that Be.FM can predict behaviors, infer characteristics of individuals and populations, generate insights about contexts, and apply behavioral science knowledge.

Problem

• Modeling and understanding human behavior using foundation models
• Predicting human decision-making with diverse behavioral data
• Inferring individual and population characteristics from behavior

Innovation

• Open foundation model for behavior
• Fine-tuned on diverse behavioral data
• Predicts behaviors and infers characteristics