Paper Number



Designing for system trustworthiness promises to address challenges of opaqueness and uncertainty introduced through Machine Learning (ML)-based systems by allowing users to understand and interpret systems’ underlying working mechanisms. However, empirical exploration of trustworthiness measures and their effectiveness is scarce and inconclusive. We investigated how varying model confidence (70% versus 90%) and making confidence levels transparent to the user (explanatory statement versus no explanatory statement) may influence perceptions of trust and performance in an information retrieval task assisted by a conversational system. In a field experiment with 104 users, our findings indicate that neither model confidence nor transparency seem to impact trust in the conversational system. However, users’ task performance is positively influenced by both transparency and trust in the system. While this study considers the complex interplay of system trustworthiness, trust, and subsequent behavioral outcomes, our results call into question the relation between system trustworthiness and user trust.



When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.