Example-based Explanations in Machine Learning (Information Systems)

Example-based Explanations in Machine Learning (Information Systems)

Eoin Delaney, Trinity College Dublin.

25th of September 2025

Abstract: 

In this talk I will give an overview of my work and the open challenges in example-based explanations such as contrastive counterfactual explanations and class prototypes. I will argue for a shift towards more human-centered and goal orientated explanations from machine learning systems. Specifically, this talk will look at how explanations can be misleading if not appropriately grounded and I will discuss the open challenges in evaluating explanations. 

This talk falls under the general theme of responsible machine learning which also encapsulates other research areas that I am interested in such as algorithmic fairness. As I am new to the faculty, this will be a good opportunity to provide an overview of the problems that I am working on.