Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913022055809024 |
|---|---|
| author | Röber, Tabea E. Festor, Paul Goedhart, Rob Birbil, S. İlker Faisal, Aldo |
| author_facet | Röber, Tabea E. Festor, Paul Goedhart, Rob Birbil, S. İlker Faisal, Aldo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09573 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations Röber, Tabea E. Festor, Paul Goedhart, Rob Birbil, S. İlker Faisal, Aldo Human-Computer Interaction Machine Learning 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. |
| title | Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2604.09573 |