Ulrike Kuhl

postdoc

ukuhl@techfak.uni-bielefeld.de +49 521 106-12125

Room: CITEC 2-412

As a postodoctoral researcher, I seek to provide empirical evidence to inform the design, development, and deployment of explainable artifical intelligence (xAI) systems that effectively meet user needs and enhance user trust. Specifically, I focus on the usability of counterfactual explanations, simplified ‘what-if’ scenarios that explore how changes to input variables trigger different model outcomes.

In this way, I aspire to contribute to a more comprehensive understanding of the human factors involved in explainable AI, ultimately fostering the development of more user-centered and actionable explanations in AI systems.

In conjunction with my research work, I serve as the scientific coordinator of the Data-NInJA research training group, supporting young AI researchers to build trustworthy AI for seamless problem solving.

Publications:

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.

Behavioral Economics and Neuroeconomics of Environmental Values

Koundouri P, Hammer B, Kuhl U, Velias A (2023)
Annual Review of Resource Economics 15(1): 153-176.

For Better or Worse: The Impact of Counterfactual Explanations’ Directionality on User Behavior in xAI

Kuhl U, Artelt A, Hammer B (2023)
In: Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Longo L (Ed); Communications in Computer and Information Science. Cham: Springer Nature Switzerland: 280-300.

Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting

Kuhl U, Artelt A, Hammer B (2022)
In: 2022 ACM Conference on Fairness, Accountability, and Transparency. New York, NY, USA: ACM: 2125-2137.

Schlussbericht ITS.ML: Intelligente Technische Systeme der nächsten Generation durch Maschinelles Lernen. Forschungsvorhaben zur automatisierten Analyse von Daten mittels Maschinellen Lernens

Hammer B, Hüllermeier E, Lohweg V, Schneider A, Schenck W, Kuhl U, Braun M, Pfeifer A, Holst C-A, Schmidt M, Schomaker G, et al. (2022)
Bielefeld: Univ. Bielefeld, Forschungsinstitut für Kognition und Robotik.

Mathematical learning deficits originate in early childhood from atypical development of a frontoparietal brain network

Kuhl U, Sobotta S, Skeide MA (2021)
PLOS Biology 19(9): e3001407.

Intuitiveness in Active Teaching

Göpfert JP, Kuhl U, Hindemith L, Wersing H, Hammer B (2021)
IEEE Transactions on Human-Machine Systems: 1-10.

Resting-State Functional Connectivity in Mathematical Expertise

Shim M, Hwang H-J, Kuhl U, Jeon H-A (2021)
Brain Sciences 11(4): 430.

Early cortical surface plasticity relates to basic mathematical learning

Kuhl U, Friederici AD, Emmrich F, Brauer J, Wilcke A, Neef N, Boltze J, Kirsten H, Schaadt G, Müller B, Kraft I, et al. (2020)
NeuroImage 204: 116235.

The emergence of dyslexia in the developing brain

Kuhl U, Neef NE, Kraft I, Schaadt G, Dörr L, Brauer J, Czepezauer I, Müller B, Wilcke A, Kirsten H, Emmrich F, et al. (2020)
NeuroImage 211: 116633.

Mathematical expertise modulates the architecture of dorsal and cortico-thalamic white matter tracts

Jeon H-A, Kuhl U, Friederici AD (2019)
Scientific Reports 9(1): 6825.

The brain basis of emerging literacy and numeracy skills. Longitudinal neuroimaging evidence from kindergarten to primary school

Kuhl U (2019)
Leipzig: Universität Leipzig.