Human-AI Construction of Bayesian Networks for Operational Decision Support via a Virtual Survey Approach

Jul 17, 2026

Researchers introduce a methodology that leverages large language models (LLMs) to construct Bayesian Belief Networks (BBNs) by simulating expert panels. AI agents, each assigned specific personas, estimate probabilities, and a trimmed-mean rule is used to mitigate noise. Demonstrated on modeling customer intention to consult a doctor, the approach finds that subjective norms exert a stronger causal influence than self-efficacy.

Why it matters: This work presents a novel hybrid human-AI method for building Bayesian networks, offering a practical solution for decision support in contexts with limited expert knowledge or data.

Full story at: arXiv AI/ML ↗