Affiliation:
1. Delft University of Technology, The Netherlands
2. Delft University of Technology and University of Leiden, The Netherlands
Abstract
In teams composed of humans, we use trust in others to make decisions, such as what to do next, who to help and who to ask for help. When a team member is artificial, they should also be able to assess whether a human teammate is trustworthy for a certain task. We see trustworthiness as the combination of (1) whether someone will do a task and (2) whether they can do it. With building beliefs in trustworthiness as an ultimate goal, we explore which internal factors (krypta) of the human may play a role (e.g., ability, benevolence, and integrity) in determining trustworthiness, according to existing literature. Furthermore, we investigate which observable metrics (manifesta) an agent may take into account as cues for the human teammate’s krypta in an online 2D grid-world experiment (
n
= 54). Results suggest that cues of ability, benevolence and integrity influence trustworthiness. However, we observed that trustworthiness is mainly influenced by human’s playing strategy and cost-benefit analysis, which deserves further investigation. This is a first step towards building informed beliefs of human trustworthiness in human-AI teamwork.
Funder
Delft AI Initiative and by the TAILOR Connectivity Fund
National Science Foundation
European Commission
Humane AI: Toward AI Systems That Augment and Empower Humans by Understanding Us, our Society and the World Around Us
Publisher
Association for Computing Machinery (ACM)
Subject
Artificial Intelligence,Human-Computer Interaction
Reference65 articles.
1. Barbara D. Adams Sonya Waldherr and J. Sartori. 2008. Trust in teams scale trust in leaders scale: Manual for administration and analyses. https://cradpdf.drdc-rddc.gc.ca/PDFS/unc95/p530364_A1b.pdf
2. Trust in small military teams;Adams Barbara D.;Command and Control Research Program,2002
3. Addressing people’s current and future states in a reinforcement learning algorithm for persuading to quit smoking and to be physically active;Albers Nele;Plos One,2022
4. Nele Albers Mark A. Neerincx and Willem-Paul Brinkman. 2022. Addressing people’s current and future states in a reinforcement learning algorithm for persuading to quit smoking and to be physically active: Data and analysis code. Version 2. 4TU.ResearchData. dataset.
5. Heterogeneous human–robot task allocation based on artificial trust;Ali Arsha;Scientific Reports,2022