On the Relation of Trust and Explainability: Why to Engineer for Trustworthiness

08/11/2021
by   Lena Kästner, et al.
0

Recently, requirements for the explainability of software systems have gained prominence. One of the primary motivators for such requirements is that explainability is expected to facilitate stakeholders' trust in a system. Although this seems intuitively appealing, recent psychological studies indicate that explanations do not necessarily facilitate trust. Thus, explainability requirements might not be suitable for promoting trust. One way to accommodate this finding is, we suggest, to focus on trustworthiness instead of trust. While these two may come apart, we ideally want both: a trustworthy system and the stakeholder's trust. In this paper, we argue that even though trustworthiness does not automatically lead to trust, there are several reasons to engineer primarily for trustworthiness – and that a system's explainability can crucially contribute to its trustworthiness.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/13/2019

What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use

Translating machine learning (ML) models effectively to clinical practic...
research
08/31/2022

Are we measuring trust correctly in explainability, interpretability, and transparency research?

This paper presents an argument for why we are not measuring trust suffi...
research
01/03/2019

Towards a Framework Combining Machine Ethics and Machine Explainability

We find ourselves surrounded by a rapidly increasing number of autonomou...
research
12/25/2020

Modeling Dispositional and Initial learned Trust in Automated Vehicles with Predictability and Explainability

Technological advances in the automotive industry are bringing automated...
research
08/10/2021

Modeling and Evaluating Personas with Software Explainability Requirements

This work focuses on the context of software explainability, which is th...
research
05/27/2021

"Why Would I Trust Your Numbers?" On the Explainability of Expected Values in Soccer

In recent years, many different approaches have been proposed to quantif...
research
09/19/2023

Incentivized Third Party Collateralization for Stablecoins

Stablecoins, which are primarily intended to function as a global reserv...

Please sign up or login with your details

Forgot password? Click here to reset