Paper-Conference

It's Not Just the Prompt: Model Choice Dominates LLM Creative Output
Prompt engineering is often treated as a reliable control mechanism for LLM behavior, yet LLM outputs vary even under similar prompts …
Jennifer Haase, Jana Gonnermann-Müller, Paul H. P. Hanel, Nicolas Leins, Thomas Kosch, Jan Mendling, Sebastian Pokutta
PDF Cite DOI
Maintaining Stable Personas? Examining Temporal Stability in LLM-Based Human Simulation
Large language models (LLMs) are increasingly employed in HumanComputer Interaction (HCI) research to simulate human behavior for …
Jana Gonnermann-Müller, Jennifer Haase, Nicolas Leins, Thomas Kosch, Sebastian Pokutta
PDF Cite DOI
The AI Accomplice: Exploring Generative Artificial Intelligence in Facilitating and Amplifying Deceptive Designs
As generative Artificial Intelligence (AI) becomes increasingly embedded and utilized for digital design, it presents both …
Thomas Kosch, Veronika Krauß, Christopher Katins, Dominik Schön, Mark McGill, Jan Gugenheimer
PDF Cite DOI
Topic Matters: How Linguistic Properties can Shape Reading Behaviour in Selective Exposure Studies
Research on selective exposure frequently relies on eye tracking to study reading behaviour, often assuming that texts across different …
Thomas Krämer, Dagmar Kern, Thomas Kosch, Daniel Hienert
PDF Cite DOI
Can AI Route You to Happiness? A Technical Study on Affective Automotive Navigation Interfaces
Conventional navigation systems, fixated on metrics such as time and distance, neglect the driver’s emotional well-being, despite …
David Bethge, Daniel Bulanda, Adam Kozlowski, Albrecht Schmidt, Tobias Grosse-Puppendahl, Thomas Kosch
PDF Cite DOI
Comfort Is in the Air: Investigating the Perceived Comfort of Rotational and Translational Mid-Air Interactions
The degrees of freedom of our arms allow us to easily translate and rotate our hands in front of our bodies. As such, most of the …
Dominik Schön, Thomas Kosch, Martin Schmitz, Sebastian Günther, Max Mühlhäuser, Florian Müller
PDF Cite DOI
Making Complex Workflows Tangible: Investigating Immersive Analytics Approaches for Data Analysis Workflows
Data Analysis Workflows (DAWs) are central to modern scientific research, yet their growing complexity presents significant usability …
PDF Cite DOI
Making Eye Contact Accessible: Augmenting Gaze in Job Interviews for People with Visual Impairments
Job interviews rely heavily on nonverbal communication, with gaze serving as a central signal of attentiveness and competence. For …
Markus Wieland, Kathrin Schnizer, Francesco Chiossi, Nina Doerr, Florian Lang, Thomas Kosch, Michael Sedlmair
PDF Cite DOI
Route2Vec: Enabling Eficient Use of Driving Context through Contextualized Route Representations
Understanding how vehicle occupants experience their journey is key to designing adaptive in-car systems. The environments they This …
Philipp Hallgarten, Thomas Kosch, Tobias Grosse-Puppendahl, Enkelejda Kasneci
PDF Cite DOI
The Impostor is Among Us: Can Large Language Models Capture the Complexity of Human Personas?
Large Language Models (LLMs) created new opportunities for generating personas, expected to streamline and accelerate the humancentered …
Christopher Lazik, Christopher Katins, Charlotte Kauter, Jonas Jakob, Caroline Jay, Lars Grunske, Thomas Kosch
PDF Cite DOI