Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability

LV Herm, K Heinrich, J Wanner, C Janiesch - International Journal of …, 2023 - Elsevier
Abstract Machine learning algorithms enable advanced decision making in contemporary
intelligent systems. Research indicates that there is a tradeoff between their model …

From symbolic RPA to intelligent RPA: challenges for developing and operating intelligent software robots

LV Herm, C Janiesch, HA Reijers, F Seubert - … Process Management: 19th …, 2021 - Springer
Robotic process automation (RPA) is a novel technology that automates tasks by interacting
with other software through their respective user interfaces. The technology has received …

Impact of explainable ai on cognitive load: Insights from an empirical study

LV Herm - arXiv preprint arXiv:2304.08861, 2023 - arxiv.org
While the emerging research field of explainable artificial intelligence (XAI) claims to
address the lack of explainability in high-performance machine learning models, in practice …

[PDF][PDF] Ask Smart to get smart: Mathematische Ausgaben generativer KI-Sprachmodelle verbessern durch gezieltes Prompt Engineering

S Schorcht, L Baumanns, N Buchholtz… - … der Gesellschaft für …, 2023 - researchgate.net
Der Beitrag beschäftigt sich mit den derzeitigen mathematischen Fähigkeiten des
generativen KI-Spachmodells ChatGPT in Bezug auf das Lösen mathematischer Probleme …

The effect of transparency and trust on intelligent system acceptance: Evidence from a user-based study

J Wanner, LV Herm, K Heinrich, C Janiesch - Electronic Markets, 2022 - Springer
Contemporary decision support systems are increasingly relying on artificial intelligence
technology such as machine learning algorithms to form intelligent systems. These systems …

Explainability is in the mind of the beholder: Establishing the foundations of explainable artificial intelligence

K Sokol, P Flach - arXiv preprint arXiv:2112.14466, 2021 - arxiv.org
Explainable artificial intelligence and interpretable machine learning are research domains
growing in importance. Yet, the underlying concepts remain somewhat elusive and lack …

Communicative AI Agents in Mathematical Task Design: A Qualitative Study of GPT Network Acting as a Multi-professional Team

S Schorcht, F Peters, J Kriegel - Digital Experiences in Mathematics …, 2024 - Springer
This study explores the application of communicative AI agents, specifically a network of
customized generative pretrained transformer agents, in designing mathematical tasks. It …

A social evaluation of the perceived goodness of explainability in machine learning

J Wanner, LV Herm, K Heinrich… - Journal of Business …, 2022 - Taylor & Francis
Machine learning in decision support systems already outperforms pre-existing statistical
methods. However, their predictions face challenges as calculations are often complex and …

HIEF: a holistic interpretability and explainability framework

JP Kucklick - Journal of Decision Systems, 2024 - Taylor & Francis
Many applications are driven by Machine Learning (ML) today. While complex ML models
lead to an accurate prediction, their inner decision-making is obfuscated. However …

What does evaluation of explainable artificial intelligence actually tell us? A case for compositional and contextual validation of XAI building blocks

K Sokol, JE Vogt - Extended Abstracts of the CHI Conference on Human …, 2024 - dl.acm.org
Despite significant progress, evaluation of explainable artificial intelligence remains elusive
and challenging. In this paper we propose a fine-grained validation framework that is not …