Using Large Language Models to Construct Virtual Top Managers: A Method for Organizational Research

TL;DR

This paper presents a novel method using large language models to create virtual top managers for organizational research, enabling simulation of decision-making based on real CEO communications and moral frameworks.

Contribution

It introduces a new framework for constructing LLM-based virtual managers that simulate real executives' decision-making processes with validated behavioral fidelity.

Findings

Virtual CEOs approximate human moral judgments.

LLM-based personas are credible tools for organizational research.

The method enables studies where direct access to executives is limited.

Abstract

This study introduces a methodological framework that uses large language models to create virtual personas of real top managers. Drawing on real CEO communications and Moral Foundations Theory, we construct LLM-based participants that simulate the decision-making of individual leaders. Across three phases, we assess construct validity, reliability, and behavioral fidelity by benchmarking these virtual CEOs against human participants. Our results indicate that theoretically scaffolded personas approximate the moral judgements observed in human samples, suggesting that LLM-based personas can serve as credible and complementary tools for organizational research in contexts where direct access to executives is limited. We conclude by outlining implications for future research using LLM-based personas in organizational settings.