For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI
Kuhl U, Artelt A, Hammer B (2023)
In: Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Longo L (Ed); Communications in Computer and Information Science. Cham: Springer Nature Switzerland: 280-300.
Sammelwerksbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Herausgeber*in
Longo, Luca
Abstract / Bemerkung
Counterfactual explanations (CFEs) are a popular approach in explainable artificial intelligence (xAI), highlighting changes to input data necessary for altering a model’s output. A CFE can either describe a scenario that is better than the factual state (upwardCFE), or a scenario that is worse than the factual state (downwardCFE). However, potential benefits and drawbacks of the directionality of CFEs for user behavior in xAI remain unclear. The current user study (N = 161) compares the impact of CFE directionality on behavior and experience of participants tasked to extract new knowledge from an automated system based on model predictions and CFEs. Results suggest thatupwardCFEs provide a significant performance advantage over other forms of counterfactual feedback. Moreover, the study highlights potential benefits ofmixedCFEs improving user performance compared todownwardCFEs or no explanations. In line with the performance results, users’ explicit knowledge of the system is statistically higher after receivingupwardCFEs compared todownwardcomparisons. These findings imply that the alignment between explanation and task at hand, the so-called regulatory fit, may play a crucial role in determining the effectiveness of model explanations, informing future research directions in (xAI). To ensure reproducible research, the entire code, underlying models and user data of this study is openly available:
Erscheinungsjahr
2023
Buchtitel
Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III
Serientitel
Communications in Computer and Information Science
Seite(n)
280-300
Konferenzdatum
2023-07-26 – 2023-07-28
ISBN
978-3-031-44069-4
eISBN
978-3-031-44070-0
ISSN
1865-0929
eISSN
1865-0937
Page URI
https://pub.uni-bielefeld.de/record/2983795
Zitieren
Kuhl U, Artelt A, Hammer B. For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI. In: Longo L, ed. Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Communications in Computer and Information Science. Cham: Springer Nature Switzerland; 2023: 280-300.
Kuhl, U., Artelt, A., & Hammer, B. (2023). For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI. In L. Longo (Ed.), Communications in Computer and Information Science. Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III (pp. 280-300). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-44070-0_14
Kuhl, Ulrike, Artelt, André, and Hammer, Barbara. 2023. “For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI”. In Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III, ed. Luca Longo, 280-300. Communications in Computer and Information Science. Cham: Springer Nature Switzerland.
Kuhl, U., Artelt, A., and Hammer, B. (2023). “For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI” in Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III, Longo, L. ed. Communications in Computer and Information Science (Cham: Springer Nature Switzerland), 280-300.
Kuhl, U., Artelt, A., & Hammer, B., 2023. For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI. In L. Longo, ed. Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Communications in Computer and Information Science. Cham: Springer Nature Switzerland, pp. 280-300.
U. Kuhl, A. Artelt, and B. Hammer, “For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI”, Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III, L. Longo, ed., Communications in Computer and Information Science, Cham: Springer Nature Switzerland, 2023, pp.280-300.
Kuhl, U., Artelt, A., Hammer, B.: For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI. In: Longo, L. (ed.) Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Communications in Computer and Information Science. p. 280-300. Springer Nature Switzerland, Cham (2023).
Kuhl, Ulrike, Artelt, André, and Hammer, Barbara. “For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI”. Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Ed. Luca Longo. Cham: Springer Nature Switzerland, 2023. Communications in Computer and Information Science. 280-300.
Google Scholar
ISBN Suche