Towards better explainability in the field of information retrieval, we present CREDENCE, an interactive tool capable of generating counterfactual explanations for document rankers. Embracing the unique properties of the ranking problem, we present counterfactual explanations in terms of document perturbations, query perturbations, and even other documents. Additionally, users may build and test their own perturbations, and extract insights about their query, documents, and ranker.
@article{arxiv.2302.04983,
title = {CREDENCE: Counterfactual Explanations for Document Ranking},
author = {Joel Rorseth and Parke Godfrey and Lukasz Golab and Mehdi Kargar and Divesh Srivastava and Jaroslaw Szlichta},
journal= {arXiv preprint arXiv:2302.04983},
year = {2023}
}