Explanations play a variety of roles in various recommender systems, from a legally mandated afterthought, through an integral element of user experience, to a key to persuasiveness. A natural and useful form of an explanation is the Counterfactual Explanation (CE). We present a method for generating highly plausible CEs in recommender systems and evaluate it both numerically and with a user study.
@article{arxiv.2507.07919,
title = {Plausible Counterfactual Explanations of Recommendations},
author = {Jakub Černý and Jiří Němeček and Ivan Dovica and Jakub Mareček},
journal= {arXiv preprint arXiv:2507.07919},
year = {2025}
}