From Facts to Foils: Designing and Evaluating Counterfactual Explanations for Smart Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912626386141184 |
|---|---|
| author | Trapp, Anna Sadeghi, Mersedeh Vogelsang, Andreas |
| author_facet | Trapp, Anna Sadeghi, Mersedeh Vogelsang, Andreas |
| contents | Explainability is increasingly seen as an essential feature of rule-based smart environments. While counterfactual explanations, which describe what could have been done differently to achieve a desired outcome, are a powerful tool in eXplainable AI (XAI), no established methods exist for generating them in these rule-based domains. In this paper, we present the first formalization and implementation of counterfactual explanations tailored to this domain. It is implemented as a plugin that extends an existing explanation engine for smart environments. We conducted a user study (N=17) to evaluate our generated counterfactuals against traditional causal explanations. The results show that user preference is highly contextual: causal explanations are favored for their linguistic simplicity and in time-pressured situations, while counterfactuals are preferred for their actionable content, particularly when a user wants to resolve a problem. Our work contributes a practical framework for a new type of explanation in smart environments and provides empirical evidence to guide the choice of when each explanation type is most effective. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03078 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Facts to Foils: Designing and Evaluating Counterfactual Explanations for Smart Environments Trapp, Anna Sadeghi, Mersedeh Vogelsang, Andreas Artificial Intelligence Software Engineering Explainability is increasingly seen as an essential feature of rule-based smart environments. While counterfactual explanations, which describe what could have been done differently to achieve a desired outcome, are a powerful tool in eXplainable AI (XAI), no established methods exist for generating them in these rule-based domains. In this paper, we present the first formalization and implementation of counterfactual explanations tailored to this domain. It is implemented as a plugin that extends an existing explanation engine for smart environments. We conducted a user study (N=17) to evaluate our generated counterfactuals against traditional causal explanations. The results show that user preference is highly contextual: causal explanations are favored for their linguistic simplicity and in time-pressured situations, while counterfactuals are preferred for their actionable content, particularly when a user wants to resolve a problem. Our work contributes a practical framework for a new type of explanation in smart environments and provides empirical evidence to guide the choice of when each explanation type is most effective. |
| title | From Facts to Foils: Designing and Evaluating Counterfactual Explanations for Smart Environments |
| topic | Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2510.03078 |