[HTML][HTML] Leveraging explainable AI for informed building retrofit decisions: Insights from a survey

D Leuthe, J Mirlach, S Wenninger, C Wiethe - Energy and buildings, 2024 - Elsevier
Accurate predictions of building energy consumption are essential for reducing the energy
performance gap. While data-driven energy quantification methods based on machine …

Eye tracking insights into physician behaviour with safe and unsafe explainable AI recommendations

M Nagendran, P Festor, M Komorowski… - NPJ Digital …, 2024 - nature.com
We studied clinical AI-supported decision-making as an example of a high-stakes setting in
which explainable AI (XAI) has been proposed as useful (by theoretically providing …

Explanations considered harmful: the impact of misleading explanations on accuracy in hybrid human-ai decision making

F Cabitza, C Fregosi, A Campagner… - World conference on …, 2024 - Springer
Explainable AI (XAI) has the potential to enhance decision-making in human-AI
collaborations, yet existing research indicates that explanations can also lead to undue …

Raising the Stakes: Performance Pressure Improves AI-Assisted Decision Making

N Haduong, NA Smith - arXiv preprint arXiv:2410.16560, 2024 - arxiv.org
AI systems are used in many domains to assist with decision making, and although the
potential for AI systems to assist with decision making is much discussed, human-AI …

Human-AI collaboration: Unraveling the effects of user proficiency and AI agent capability in intelligent decision support systems

L Peng, D Li, Z Zhang, T Zhang, A Huang… - International Journal of …, 2024 - Elsevier
Artificial intelligence (AI) agents are integral components of modern intelligent decision
support systems (IDSS), providing their capability to assist in decision-making processes …

VIME: Visual Interactive Model Explorer for Identifying Capabilities and Limitations of Machine Learning Models for Sequential Decision-Making

A Das Antar, S Molaei, YY Chen, ML Lee… - Proceedings of the 37th …, 2024 - dl.acm.org
Ensuring that Machine Learning (ML) models make correct and meaningful inferences is
necessary for the broader adoption of such models into high-stakes decision-making …

Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting

M Kayser, B Menzat, C Emde, B Bercean… - arXiv preprint arXiv …, 2024 - arxiv.org
The growing capabilities of AI models are leading to their wider use, including in safety-
critical domains. Explainable AI (XAI) aims to make these models safer to use by making …

Evaluating the Influences of Explanation Style on Human-AI Reliance

E Casolin, FD Salim, B Newell - arXiv preprint arXiv:2410.20067, 2024 - arxiv.org
Explainable AI (XAI) aims to support appropriate human-AI reliance by increasing the
interpretability of complex model decisions. Despite the proliferation of proposed methods …

(X) AI as a Teacher: Learning with Explainable Artificial Intelligence

P Spitzer, M Goutier, N Kühl, G Satzger - Proceedings of Mensch und …, 2024 - dl.acm.org
Due to changing demographics, limited availability of experts, and frequent job transitions,
retaining and sharing knowledge within organizations is crucial. While many learning …

Don't be Fooled: The Misinformation Effect of Explanations in Human-AI Collaboration

P Spitzer, J Holstein, K Morrison, K Holstein… - arXiv preprint arXiv …, 2024 - arxiv.org
Across various applications, humans increasingly use black-box artificial intelligence (AI)
systems without insight into these systems' reasoning. To counter this opacity, explainable AI …