Work

Introducing a Research Tool to Increase the Validity of Scenario-Based Experiments on Human-AI Collaboration

Year: 2026

Type: conference-paper

Abstract: To address the limitations of traditional vignette methodologies, this study introduces the Managerial Interaction and Response to Artificial Intelligence, a tool for examining how managers engage with AI. Conventional vignettes often fail to capture the complexity of real-world human-AI interactions because they lack realism and interactivity. This new tool enhances contextual accuracy, interactivity, and ecological validity by integrating advanced large language models into a reasoning-and-action framework. Using a dynamic yet controlled conversational AI environment, we enable participants to interact with AI systems naturally while maintaining experimental rigor and realism. Its design mitigates risks, including irrelevant AI responses, ensuring reliable and data-driven interactions. Evaluation results indicate that it performs effectively across diverse question types, marking a significant advancement in the study of AI-manager collaboration and supporting research.

Source: International Conference on e-Education, e-Business, e-Management and e-Learning

DOI: 10.1109/ic4e69618.2026.11631610

Authors: Grzegorz Leszczyński, Piotr Gaczek, Amira Mouakher

Institutions: Poznań University of Economics and Business, Université de Perpignan

Language: English

Topic: Human-Automation Interaction and Safety

Subfield: Human Factors and Ergonomics

Field: Social Sciences

Domain: Social Sciences

Open Access status: hybrid

OpenAlex ID: W7202292952

FWCI:

Cites: 32

Cited by:

Related to: 10