Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI

Abstract

We introduce a novel metric for measuring semantic continuity in Explainable AI methods and machine learning models. We posit that for models to be truly interpretable and trustworthy, similar inputs should yield similar explanations, reflecting a consistent semantic understanding. By leveraging XAI techniques, we assess semantic continuity in the task of image recognition. We conduct experiments to observe how incremental changes in input affect the explanations provided by different XAI methods. Through this approach, we aim to evaluate the models' capability to generalize and abstract semantic concepts accurately and to evaluate different XAI methods in correctly capturing the model behaviour. This paper contributes to the broader discourse on AI interpretability by proposing a quantitative measure for semantic continuity for XAI methods, offering insights into the models' and explainers' internal reasoning processes, and promoting more reliable and transparent AI systems.

25 pages, accepted at the world conference of explainable AI, 2024, Malta

References in corpus (5)

• Measuring and testing dependence by correlation of distances
• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
• OmniXAI: A Library for Explainable AI
• Why Should I Choose You? AutoXAI: A Framework for Selecting and Tuning eXplainable AI Solutions