VitrAI -- Applying Explainable AI in the Real World

TL;DR

VitrAI is a web-based platform that evaluates and demonstrates four XAI methods across real-world scenarios, highlighting practical challenges and assessing explanation quality for human understanding.

Contribution

This work introduces VitrAI, a novel platform for practical evaluation of multiple XAI algorithms in real-world contexts.

Findings

Identifies practical obstacles in adopting XAI methods.

Provides qualitative assessments of explanation quality.

Demonstrates differences in XAI performance across scenarios.

Abstract

With recent progress in the field of Explainable Artificial Intelligence (XAI) and increasing use in practice, the need for an evaluation of different XAI methods and their explanation quality in practical usage scenarios arises. For this purpose, we present VitrAI, which is a web-based service with the goal of uniformly demonstrating four different XAI algorithms in the context of three real life scenarios and evaluating their performance and comprehensibility for humans. This work reveals practical obstacles when adopting XAI methods and gives qualitative estimates on how well different approaches perform in said scenarios.