Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning
Kuhl U, Artelt A, Hammer B (2023)
Frontiers in Computer Science 5: 1087929.
Zeitschriftenaufsatz
| Veröffentlicht | Englisch
Download
fcomp-05-1087929.pdf
2.91 MB
Autor*in
Projekt
GRK Data-NInJa: Standortübergreifendes Graduiertenkolleg
Water-Futures - Smart Water Futures: designing the next generation of urban drinking water systems
IMPACT-ML: The implications of conversing with intelligent machines in everyday life on people's beliefs about algorithms, their communication behavior and their relationship building
Water-Futures - Smart Water Futures: designing the next generation of urban drinking water systems
IMPACT-ML: The implications of conversing with intelligent machines in everyday life on people's beliefs about algorithms, their communication behavior and their relationship building
Abstract / Bemerkung
**Introduction**
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic of active research, offering approaches to address the “how” and “why” of automated decision-making. Within this domain, counterfactual explanations (CFEs) have gained considerable traction as a psychologically grounded approach to generatepost-hocexplanations. To do so, CFEs highlight what changes to a model's input would have changed its prediction in a particular way. However, despite the introduction of numerous CFE approaches, their usability has yet to be thoroughly validated at the human level. **Methods**
To advance the field of XAI, we introduce the Alien Zoo, an engaging, web-based and game-inspired experimental framework. The Alien Zoo provides the means to evaluate usability of CFEs for gaining new knowledge from an automated system, targeting novice users in a domain-general context. As a proof of concept, we demonstrate the practical efficacy and feasibility of this approach in a user study. **Results**
Our results suggest the efficacy of the Alien Zoo framework for empirically investigating aspects of counterfactual explanations in a game-type scenario and a low-knowledge domain. The proof of concept study reveals that users benefit from receiving CFEs compared to no explanation, both in terms of objective performance in the proposed iterative learning task, and subjective usability.
To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic of active research, offering approaches to address the “how” and “why” of automated decision-making. Within this domain, counterfactual explanations (CFEs) have gained considerable traction as a psychologically grounded approach to generatepost-hocexplanations. To do so, CFEs highlight what changes to a model's input would have changed its prediction in a particular way. However, despite the introduction of numerous CFE approaches, their usability has yet to be thoroughly validated at the human level. **Methods**
To advance the field of XAI, we introduce the Alien Zoo, an engaging, web-based and game-inspired experimental framework. The Alien Zoo provides the means to evaluate usability of CFEs for gaining new knowledge from an automated system, targeting novice users in a domain-general context. As a proof of concept, we demonstrate the practical efficacy and feasibility of this approach in a user study. **Results**
Our results suggest the efficacy of the Alien Zoo framework for empirically investigating aspects of counterfactual explanations in a game-type scenario and a low-knowledge domain. The proof of concept study reveals that users benefit from receiving CFEs compared to no explanation, both in terms of objective performance in the proposed iterative learning task, and subjective usability.
Stichworte
explainable AI;
human-grounded evaluation;
user study;
experimental framework;
counterfactual explanations;
usability;
human-computer interaction
Erscheinungsjahr
2023
Zeitschriftentitel
Frontiers in Computer Science
Band
5
Art.-Nr.
1087929
Urheberrecht / Lizenzen
Konferenzdatum
2023-03-21 – 2023-03-21
eISSN
2624-9898
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2969734
Zitieren
Kuhl U, Artelt A, Hammer B. Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning. Frontiers in Computer Science. 2023;5: 1087929.
Kuhl, U., Artelt, A., & Hammer, B. (2023). Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning. Frontiers in Computer Science, 5, 1087929. https://doi.org/10.3389/fcomp.2023.1087929
Kuhl, Ulrike, Artelt, André, and Hammer, Barbara. 2023. “Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning”. Frontiers in Computer Science 5: 1087929.
Kuhl, U., Artelt, A., and Hammer, B. (2023). Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning. Frontiers in Computer Science 5:1087929.
Kuhl, U., Artelt, A., & Hammer, B., 2023. Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning. Frontiers in Computer Science, 5: 1087929.
U. Kuhl, A. Artelt, and B. Hammer, “Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning”, Frontiers in Computer Science, vol. 5, 2023, : 1087929.
Kuhl, U., Artelt, A., Hammer, B.: Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning. Frontiers in Computer Science. 5, : 1087929 (2023).
Kuhl, Ulrike, Artelt, André, and Hammer, Barbara. “Let's go to the Alien Zoo: Introducing an experimental framework to study usability of counterfactual explanations for machine learning”. Frontiers in Computer Science 5 (2023): 1087929.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Name
fcomp-05-1087929.pdf
2.91 MB
Access Level
Open Access
Zuletzt Hochgeladen
2023-03-21T08:44:35Z
MD5 Prüfsumme
36badcee6e8f89f19df1a914c176e486
Link(s) zu Volltext(en)
Access Level
Open Access
Export
Markieren/ Markierung löschen
Markierte Publikationen
Web of Science
Dieser Datensatz im Web of Science®Quellen
arXiv: 2205.03398
Suchen in