Explainability Pitfalls: Beyond Dark Patterns in Explainable AI

09/26/2021
by   Upol Ehsan, et al.
0

To make Explainable AI (XAI) systems trustworthy, understanding harmful effects is just as important as producing well-designed explanations. In this paper, we address an important yet unarticulated type of negative effect in XAI. We introduce explainability pitfalls(EPs), unanticipated negative downstream effects from AI explanations manifesting even when there is no intention to manipulate users. EPs are different from, yet related to, dark patterns, which are intentionally deceptive practices. We articulate the concept of EPs by demarcating it from dark patterns and highlighting the challenges arising from uncertainties around pitfalls. We situate and operationalize the concept using a case study that showcases how, despite best intentions, unsuspecting negative effects such as unwarranted trust in numerical explanations can emerge. We propose proactive and preventative strategies to address EPs at three interconnected levels: research, design, and organizational.

READ FULL TEXT
research
07/28/2021

The Who in Explainable AI: How AI Background Shapes Perceptions of AI Explanations

Explainability of AI systems is critical for users to take informed acti...
research
05/02/2022

Creative Uses of AI Systems and their Explanations: A Case Study from Insurance

Recent works have recognized the need for human-centered perspectives wh...
research
10/02/2022

"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction

Despite the proliferation of explainable AI (XAI) methods, little is und...
research
05/02/2022

TRUST XAI: Model-Agnostic Explanations for AI With a Case Study on IIoT Security

Despite AI's significant growth, its "black box" nature creates challeng...
research
09/05/2023

A Context-Sensitive Approach to XAI in Music Performance

The rapidly evolving field of Explainable Artificial Intelligence (XAI) ...
research
09/01/2020

Explainability Case Studies

Explainability is one of the key ethical concepts in the design of AI sy...
research
05/10/2023

Why Don't You Do Something About It? Outlining Connections between AI Explanations and User Actions

A core assumption of explainable AI systems is that explanations change ...

Please sign up or login with your details

Forgot password? Click here to reset