Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations

Tabea E. Röber; Paul Festor; Rob Goedhart; S. İlker Birbil; Aldo Faisal

cs.HCFeb 22, 2026

Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations

Authors: Tabea E. Röber, Paul Festor, Rob Goedhart, S. İlker Birbil, Aldo Faisal

Organizations: Amsterdam Business School, University of Amsterdam, The Netherlands · Department of Bioengineering, Imperial College London, UK · Institute of Artificial and Human Intelligence, University of Bayreuth, Germany

Abstract

Experimental user studies evaluating the effectiveness of different subtypes of post-hoc explanations for black-box models are largely nonexistent. Therefore, the aim of this study was to investigate and evaluate how different types of counterfactual explanations, namely single point explanations and interval-based explanations, affect both model understanding and (demonstrated) trust. We conducted an online user study using a within-subjects experimental design, where the experimental arms were (i) no explanation (control), (ii) feature importance scores, (iii) point counterfactual explanations, and (iv) interval counterfactual explanations. Our results clearly show the superiority of interval explanations over other tested explanation types in increasing both model understanding and demonstrated trust in the AI. We could not support findings of some previous studies showing an effect of point counterfactual explanations compared to the control group. Our results further highlight the role individual differences in, for example, cognitive style or personality, in explanation effectiveness.

Figures & tables

Figure 1: Schematic overview of the study concept and design. After filling out a survey to record demographics and experience level, each participant completes three blocks consisting of multiple trials each. Instructions within a block do not change. Participants are randomly assigned to one of the four explanation groups and one of the three different view modes.

Panel of Figure 2 — Figure 2: Model-based group means by explanation type from two mixed-effects models with participant-level random intercepts, controlling for gender , education , and age . Estimates are based on 100 bootstrapped samples per model. Error bars reflect bootstrapped standard deviations. Group means are estimated for the reference groups ( female and bachelors ) and the mean age observed in the sample.

Panel of Figure 3 — Figure 3: Root mean squared error (RMSE) by following behavior vs reliance on AI proportion, for trials where no features are hidden and where three out of 10 features are hidden. Each user is represented by two dots (unless the proportion is 0 or 1). A LOWESS curve is shown to visualize trends in prediction error.

Panel of Figure 4 — Figure 4: Observed group means averaged per user by explanation type and gender.

Feature	Description	Type
zipcode	zipcode corresponding to the area the house is located in	categorical (4)
lot-len	the length in meters of the plot of land the house is built on	float
lot-width	the width in meters of the plot of land the house is built on	float
lot-area	the total area of the plot of land the house is built on	float
house-area	the living area of the house in square meters	float
garden-size	the size of the garden in square meters	float

Table 1: Overview of features included in the housing dataset utilized in this study

Figure 5: Distribution of participants over conditions

Counterfactual Explanations

Counterfactual explanations show how changing an input could alter a model’s prediction, supporting model understanding, auditing, and actionable recourse.

See all 115 papers

Do Metrics for Counterfactual Explanations Align with User Perception?
Mar 16, 2026Felix Liedeker, Basil Ell, Philipp Cimiano +1Counterfactual Evaluation Explainability Evaluation
Bielefeld University, Bielefeld, Germany
Taking the Whys Seriously: Limitations of Counterfactual Explanations in Justification and Recourse
Aug 31, 2026Mattia Cerrato, Otto Sahlgren, Xenia HeilmannCounterfactual Explanations AI Accountability
Johannes Gutenberg University Mainz, Germany · University of Tampere, Finland
CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations
Apr 30, 2026Louth Bin Rawshan, Zhuoyu Wang, Brian Y. LimFeature Attribution Explainable Artificial Intelligence
National University of Singapore, Singapore

Mar 16, 2026J/K move · Enter open · S save

Do Metrics for Counterfactual Explanations Align with User Perception?

Felix Liedeker, Basil Ell, Philipp Cimiano, Christoph Düsing

Bielefeld University, Bielefeld, Germany

Counterfactual Evaluation Explainability Evaluation Counterfactual Explanations

Open paper AskPDF arXiv

Explainability is widely regarded as essential for trustworthy artificial intelligence systems. However, the metrics commonly used to evaluate counterfactual explanations are algorithmic evaluation metrics that are rarely validated against human judgments of explanation quality. This raises the question of whether such metrics meaningfully reflect user perceptions. We address this question through an empirical study that directly compares algorithmic evaluation metrics with human judgments across three datasets. Participants rated counterfactual explanations along multiple dimensions of perceived quality, which we relate to a comprehensive set of standard counterfactual metrics. We analyze both individual relationships and the extent to which combinations of metrics can predict human assessments. Our results show that correlations between algorithmic metrics and human ratings are generally weak and strongly dataset-dependent. Moreover, increasing the number of metrics used in predictive models does not lead to reliable improvements, indicating structural limitations in how current metrics capture criteria relevant for humans. Overall, our findings suggest that widely used counterfactual evaluation metrics fail to reflect key aspects of explanation quality as perceived by users, underscoring the need for more human-centered approaches to evaluating explainable artificial intelligence.

Abstract

Counterfactual Explanations

Explore similar work

Do Metrics for Counterfactual Explanations Align with User Perception?

Taking the Whys Seriously: Limitations of Counterfactual Explanations in Justification and Recourse

CoAX: Cognitive-Oriented Attribution eXplanation User Model of Human Understanding of AI Explanations