Intent-Aware Example-Based Explainability

Abstract

In this PhD research, I aim to investigate the limitations inherent in current example-based explainability methods, develop solutions to address these deficiencies, and propose a novel direction for research that aligns example-based explainability with user needs and intent. The objectives of this research include: (a) Formalize existing evaluation metrics for local example-based explainability and propose new metrics to assess these methods from user perspectives; (b) Develop a framework for intent-aware local example-based explainability; and (c) Extend the framework for global example-based explainability and generate model-aware, faithful explanations.