Counterfactual Explanations Under Model Multiplicity and Their Use in Computational Argumentation
Abstract
Counterfactual explanations (CXs) are widely recognised as an essential technique for providing recourse recommendations for AI models. However, it is not obvious how to determine CXs in model multiplicity scenarios, where equally performing but different models can be obtained for the same task. In this paper, we propose novel qualitative and quantitative definitions of CXs based on explicit, nested quantification over (groups) of model decisions. We also study properties of these notions and identify decision problems of interest therefor. While our CXs are broadly applicable, in this paper we instantiate them within computational argumentation where model multiplicity naturally emerges, e.g. with incomplete and case-based argumentation frameworks. We then illustrate the suitability of our CXs for model multiplicity in legal and healthcare contexts, before analysing the complexity of the associated decision problems.
Cite
Text
Alfano et al. "Counterfactual Explanations Under Model Multiplicity and Their Use in Computational Argumentation." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/481Markdown
[Alfano et al. "Counterfactual Explanations Under Model Multiplicity and Their Use in Computational Argumentation." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/alfano2025ijcai-counterfactual/) doi:10.24963/IJCAI.2025/481BibTeX
@inproceedings{alfano2025ijcai-counterfactual,
title = {{Counterfactual Explanations Under Model Multiplicity and Their Use in Computational Argumentation}},
author = {Alfano, Gianvincenzo and Gould, Adam and Leofante, Francesco and Rago, Antonio and Toni, Francesca},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2025},
pages = {4321-4329},
doi = {10.24963/IJCAI.2025/481},
url = {https://mlanthology.org/ijcai/2025/alfano2025ijcai-counterfactual/}
}