Predicting Satisfaction of Counterfactual Explanations from Human Ratings of Explanatory Qualities
Open Access
- 12 October 2025
- book chapter
- Published by Springer Nature
- p. 210-229
Abstract
Counterfactual explanations are a widely used approach in Explainable AI, offering actionable insights into decision-making by illustrating how small changes to input data can lead to different outcomes. Despite their importance, evaluating the quality of counterfactual explanations remains an open problem. Traditional quantitative metrics, such as sparsity or proximity, fail to fully account for human preferences in explanations, while user studies are insightful but not scalable. Moreover, relying only on a single overall satisfaction rating does not lead to a nuanced understanding of why certain explanations are effective or not. To address this, we analyze a dataset of counterfactual explanations that were evaluated by 206 human participants, who rated not only overall satisfaction but also seven explanatory criteria: feasibility, coherence, complexity, understandability, completeness, fairness, and trust. Modeling overall satisfaction as a function of these criteria, we find that feasibility (the actionability of suggested changes) and trust (the belief that the changes would lead to the desired outcome) consistently stand out as the strongest predictors of user satisfaction, though completeness also emerges as a meaningful contributor. Crucially, even excluding feasibility and trust, other metrics explain 58% of the variance, highlighting the importance of additional explanatory qualities. Complexity appears independent, suggesting more detailed explanations do not necessarily reduce satisfaction. Strong metric correlations imply a latent structure in how users judge quality, and demographic background (e.g., medical or ML expertise) significantly affects ranking patterns, highlighting the need for context-specific designs. These insights directly inform the development of improved counterfactual algorithms, highlighting the need to tailor explanatory qualities (completeness, consistency, fairness, complexity) to diverse user expertise and specific domain contexts.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Enhancing Counterfactual Explanation Search with Diffusion Distance and Directional Coherence2024
- PreCoF: counterfactual explanations for fairnessMachine Learning, 2023
- CARE: coherent actionable recourse based on sound counterfactual explanationsInternational Journal of Data Science and Analytics, 2022
- Counterfactual explanations and how to find them: literature review and benchmarkingData Mining and Knowledge Discovery, 2022
- The false hope of current approaches to explainable artificial intelligence in health careThe Lancet Digital Health, 2021
- Interpretable Counterfactual Explanations Guided by Prototypes2021
- Are Explanations Helpful? A Comparative Study of the Effects of Explanations in AI-Assisted Decision-Making2021
- Explaining machine learning classifiers through diverse counterfactual explanations2020
- Explanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence, 2019
- Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)IEEE Access, 2018