Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box
ACM Computing Surveys · 30.06.2025 · 57 (6) · 1-37
DOI: 10.1145/3672553 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.02.2025. Verfasst von Catarina Moreira und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FCT Fundação para a Ciência e a Tecnologia, UNESCO Chair on AI&VR of the University of Lisbon.
Abstract (Originalsprache)
This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable, white-box model), a random forest (semi-interpretable, grey-box model), and a neural network (fully opaque, black-box model). We tested the counterfactual generation process using four algorithms (DiCE, WatcherCF, prototype, and GrowingSpheresCF) in the literature in 25 different datasets. Our findings indicate that: (1) Different machine learning models have little impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions are not actionable and will not provide meaningful explanations; (3) One cannot have meaningful evaluation results without guaranteeing plausibility in the counterfactual generation. Algorithms that do not consider plausibility in their internal mechanisms will lead to biased and unreliable conclusions if evaluated with the current state-of-the-art metrics; (4) A counterfactual inspection analysis is strongly recommended to ensure a robust examination of counterfactual explanations and the potential identification of biases.
Förderung
- FCT Fundação para a Ciência e a Tecnologia
- UNESCO Chair on AI&VR of the University of Lisbon
Zitieren
APA
Moreira, C., Chou, Y., Hsieh, C., Ouyang, C., Pereira, J., & Jorge, J. (2025). Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box. ACM Computing Surveys, 57(6), 1-37. https://doi.org/10.1145/3672553
Vancouver
Moreira C, Chou Y, Hsieh C, Ouyang C, Pereira J, Jorge J. Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box. ACM Computing Surveys. 2025;57(6):1-37. doi:10.1145/3672553
BibTeX
@article{Moreira2025,
author = {Moreira, Catarina and Chou, Yu-Liang and Hsieh, Chihcheng and Ouyang, Chun and Pereira, João and Jorge, Joaquim},
title = {Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {6},
pages = {1--37},
doi = {10.1145/3672553}
}
EUVIMED