A Formal Account of Trustworthiness: Connecting Intrinsic and Perceived Trustworthiness
Open Access
- 16 October 2024
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Vol. 7, 131-140
Abstract
This paper proposes a formal account of AI trustworthiness, connecting both intrinsic and perceived trustworthiness in an operational schematization. We argue that trustworthiness extends beyond the inherent capabilities of an AI system to include significant influences from observers' perceptions, such as perceived transparency, agency locus, and human oversight. While the concept of perceived trustworthiness is discussed in the literature, few attempts have been made to connect it with the intrinsic trustworthiness of AI systems. Our analysis introduces a novel schematization to quantify trustworthiness by assessing the discrepancies between expected and observed behaviors and how these affect perceived uncertainty and trust. The paper provides a formalization for measuring trustworthiness, taking into account both perceived and intrinsic characteristics. By detailing the factors that influence trust, this study aims to foster more ethical and widely accepted AI technologies, ensuring they meet both functional and ethical criteria.Keywords
This publication has 21 references indexed in Scilit:
- A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciencesArtificial Intelligence Review, 2022
- Who needs explanation and when? Juggling explainable AI and user epistemic uncertaintyInternational Journal of Human-Computer Studies, 2022
- How Robots’ Unintentional Metacommunication Affects Human–Robot Interactions. A Systemic ApproachMinds and Machines, 2021
- Mental models and expectation violations in conversational AI interactionsDecision Support Systems, 2021
- Towards Transparency by Design for Artificial IntelligenceScience and Engineering Ethics, 2020
- Exploring Explanation Effects on Consumers’ Trust in Online Recommender AgentsInternational Journal of Human–Computer Interaction, 2017
- Neuroticism's prospective association with mental disorders halves after adjustment for baseline symptoms and psychiatric history, but the adjusted association hardly decays with time: a meta-analysis on 59 longitudinal/prospective studies with 443 313 participantsPsychological Medicine, 2016
- Diagnosing the locus of trust: A temporal perspective for trustor, trustee, and dyadic influences on perceived trustworthiness.Journal of Applied Psychology, 2016
- Trust, trustworthiness, and trust propensity: A meta-analytic test of their unique relationships with risk taking and job performance.Journal of Applied Psychology, 2007
- What makes a good team player? Personality and team effectiveness.Group Dynamics: Theory, Research, and Practice, 2006