The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems

TL;DR

This study investigates whether explanations improve users' understanding of AI limitations in visual question answering, finding that explanations tend to inflate perceived competence rather than clarify actual system capabilities.

Contribution

The paper reveals that explanations do not enhance perception of AI limitations and instead increase perceived competence, challenging assumptions about explanations' role in transparency.

Findings

Explanations do not improve perception of AI limitations.

Explanations increase perceived system competence.

Users struggle to accurately assess AI capabilities.

Abstract

We examine how users perceive the limitations of an AI system when it encounters a task that it cannot perform perfectly and whether providing explanations alongside its answers aids users in constructing an appropriate mental model of the system's capabilities and limitations. We employ a visual question answer and explanation task where we control the AI system's limitations by manipulating the visual inputs: during inference, the system either processes full-color or grayscale images. Our goal is to determine whether participants can perceive the limitations of the system. We hypothesize that explanations will make limited AI capabilities more transparent to users. However, our results show that explanations do not have this effect. Instead of allowing users to more accurately assess the limitations of the AI system, explanations generally increase users' perceptions of the system's competence - regardless of its actual performance.