Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresight

TL;DR

This paper introduces the Large Behavioral Model (LBM), a fine-tuned AI system that predicts individual human strategic decisions with high accuracy by leveraging detailed psychological profiles, surpassing traditional prompting methods.

Contribution

The paper presents LBM, a novel behavioral foundation model that uses structured psychometric profiles for high-fidelity prediction of human decisions, improving over existing prompting-based approaches.

Findings

LBM outperforms unadapted Llama-3.1-8B-Instruct in behavioral prediction.

Performance improves with richer trait profiles, demonstrating scalability.

LBM is effective across diverse strategic dilemmas.

Abstract

Predicting human decision-making in high-stakes environments remains a central challenge for artificial intelligence. While large language models (LLMs) demonstrate strong general reasoning, they often struggle to generate consistent, individual-specific behavior, particularly when accurate prediction depends on complex interactions between psychological traits and situational constraints. Prompting-based approaches can be brittle in this setting, exhibiting identity drift and limited ability to leverage increasingly detailed persona descriptions. To address these limitations, we introduce the Large Behavioral Model (LBM), a behavioral foundation model fine-tuned to predict individual strategic choices with high fidelity. LBM shifts from transient persona prompting to behavioral embedding by conditioning on a structured, high-dimensional trait profile derived from a comprehensive psychometric battery. Trained on a proprietary dataset linking stable dispositions, motivational states, and situational constraints to observed choices, LBM learns to map rich psychological profiles to discrete actions across diverse strategic dilemmas. In a held-out scenario evaluation, LBM fine-tuning improves behavioral prediction relative to the unadapted Llama-3.1-8B-Instruct backbone and performs comparably to frontier baselines when conditioned on Big Five traits. Moreover, we find that while prompting-based baselines exhibit a complexity ceiling, LBM continues to benefit from increasingly dense trait profiles, with performance improving as additional trait dimensions are provided. Together, these results establish LBM as a scalable approach for high-fidelity behavioral simulation, enabling applications in strategic foresight, negotiation analysis, cognitive security, and decision support.