Artificial Intelligence and a Microperspective of Organizational Corruption

Abstract

Building on previous research on the collaborative root of corruption, we propose and conclude that people cheat more when they collaborate with another person in comparison with an artificial intelligence (AI) robot. We suggest that people infer that a human collaborator would cheat more than an AI collaborator when working together. Having drawn this ethical inference about a collaborator’s behavior, people are more likely to cheat subsequently in human-human collaboration than in human-AI collaboration. Therefore, the ethical inference about a collaborator’s behavior is the reason why people are more inclined to cheat in human-human collaboration than human-AI collaboration. We tested our theory in two lab experiments. Additionally, in two online experiments, we showed our findings were counterintuitive with regard to the common belief of laypeople. Managers are unaware of the positive effect of human-AI collaboration on reducing cheating behavior in organizations. Our research contributes to the microperspective of organizational corruption and has implications for anticorruption and compliance policies in organizations and society as a whole.