5 papers
Can Conversational XAI Improve User Performance? An Experimental Study
Sven Kruschel, Julian Rosenberger, Lasse Bohlen +2
Explainable AI (XAI) techniques aim to provide insights into predictive models and enhance user performance, yet they often fall short of these expectations. Conversational XAI ass…
Overcoming Algorithm Aversion with Transparency: Can Transparent Predictions Change User Behavior?
Lasse Bohlen, Sven Kruschel, Julian Rosenberger +2
Previous work has shown that allowing users to adjust a machine learning (ML) model's predictions can reduce aversion to imperfect algorithmic decisions. However, these results wer…
Navigating the Rashomon Effect: How Personalization Can Help Adjust Interpretable Machine Learning Models to Individual Users
Julian Rosenberger, Philipp Schröppel, Sven Kruschel +3
The Rashomon effect describes the observation that in machine learning (ML) multiple models often achieve similar predictive performance while explaining the underlying relationshi…
Quantifying Visual Properties of GAM Shape Plots: Impact on Perceived Cognitive Load and Interpretability
Sven Kruschel, Lasse Bohlen, Julian Rosenberger +2
Generalized Additive Models (GAMs) offer a balance between performance and interpretability in machine learning. The interpretability aspect of GAMs is expressed through shape plot…
Challenging the Performance-Interpretability Trade-off: An Evaluation of Interpretable Machine Learning Models
Sven Kruschel, Nico Hambauer, Sven Weinzierl +3
Machine learning is permeating every conceivable domain to promote data-driven decision support. The focus is often on advanced black-box models due to their assumed performance ad…