Towards Understanding Human-AI Reliance Patterns Through Explanation Styles DOI

Emma R. Casolin,

Flora D. Salim

Published: Sept. 22, 2024

Language: Английский

Leveraging explainable AI for informed building retrofit decisions: Insights from a survey DOI Creative Commons
Daniel Leuthe,

Jonas Mirlach,

Simon Wenninger

et al.

Energy and Buildings, Journal Year: 2024, Volume and Issue: 318, P. 114426 - 114426

Published: Sept. 1, 2024

Accurate predictions of building energy consumption are essential for reducing the performance gap. While data-driven quantification methods based on machine learning deliver promising results, lack Explainability prevents their widespread application. To overcome this, Explainable Artificial Intelligence (XAI) was introduced. However, to this point, no research has examined how effective these explanations concerning decision-makers, i.e., property owners. address we implement three transparent models (Linear Regression, Decision Tree, QLattice) and apply four XAI (Partial Dependency Plots, Accumulated Local Effects, Interpretable Model-Agnostic Explanations, Shapley Additive Explanations) an Neural Network using a real-world dataset 25,000 residential buildings. We evaluate Prediction Accuracy through survey with 137 participants considering human-centered dimensions explanation satisfaction perceived fidelity. The results quantify Explainability-Accuracy trade-off in forecasting it can be counteracted by choosing right method foster informed retrofit decisions. For research, set foundation further increasing evaluation. practice, encourage reduce acceptance gap methods, whereby should selected carefully, as within varies up 10 %.

Language: Английский

Citations

5
Explanations Considered Harmful: The Impact of Misleading Explanations on Accuracy in Hybrid Human-AI Decision Making DOI
Federico Cabitza, Caterina Fregosi, Andrea Campagner

et al.

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 255 - 269

Published: Jan. 1, 2024

Language: Английский

Citations

5
Personalized explanations for clinician-AI interaction in breast imaging diagnosis by adapting communication to expertise levels DOI Creative Commons
Francisco Maria Calisto, João Abrantes, Carlos Santiago

et al.

International Journal of Human-Computer Studies, Journal Year: 2025, Volume and Issue: unknown, P. 103444 - 103444

Published: Jan. 1, 2025

Language: Английский

Citations

0
The Influence of Curiosity Traits and On-Demand Explanations in AI-Assisted Decision-Making DOI
Federico Maria Cau, Lucio Davide Spano

Published: March 19, 2025

Language: Английский

Citations

0
Robust Relatable Explanations of Machine Learning with Disentangled Cue-specific Saliency DOI

Harshavardhan Sunil Abichandani,

W. Y. Zhang, Brian Y. Lim

et al.

Published: March 19, 2025

Language: Английский

Citations

0
Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations DOI
Indu Panigrahi, Sunnie S. Y. Kim, Amna Liaqat

et al.

Published: April 23, 2025

Language: Английский

Citations

0
Hybrid Automation Experiences – Communication, Coordination, and Collaboration within Human-AI Teams DOI
Philipp Spitzer, Matthias Baldauf, Philippe Palanque

et al.

Published: April 23, 2025

Language: Английский

Citations

0
Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation DOI
Roel W. Visser, Tobias M. Peters, Ingrid Scharlau

et al.

Cognitive Systems Research, Journal Year: 2025, Volume and Issue: unknown, P. 101357 - 101357

Published: April 1, 2025

Language: Английский

Citations

0
Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information DOI
Philipp Spitzer, Joshua Holstein, Patrick Hemmer

et al.

Proceedings of the ACM on Human-Computer Interaction, Journal Year: 2025, Volume and Issue: 9(2), P. 1 - 28

Published: May 2, 2025

The integration of artificial intelligence (AI) into human decision-making processes at the workplace presents both opportunities and challenges. One promising approach to leverage existing complementary capabilities is allowing humans delegate individual instances decision tasks AI. However, enabling effectively requires them assess several factors. key factor analysis their own those AI in context given task. In this work, we conduct a behavioral study explore effects providing contextual information support delegation decision. Specifically, investigate how about task domain influence humans' decisions an impact on human-AI team performance. Our findings reveal that access significantly improves performance settings. Finally, show behavior changes with different types information. Overall, research advances understanding computer-supported, collaborative work provides actionable insights for designing more effective systems.

Language: Английский

Citations

0
Human-AI collaboration: Unraveling the effects of user proficiency and AI agent capability in intelligent decision support systems DOI
Lu Elfa Peng,

Dailin Li,

Zhaotong Zhang

et al.

International Journal of Industrial Ergonomics, Journal Year: 2024, Volume and Issue: 103, P. 103629 - 103629

Published: Aug. 12, 2024

Language: Английский

Citations

3