From July 13 to July 16, 2026, the 31st Annual ACM Conference on Intelligent User Interfaces (IUI 2026) took place at the St Raphael Resort & Marina in Limassol, Cyprus. As a premier international venue ranked ‘A‘ according to ICORE, the ACM IUI conference brings together researchers and practitioners at the intersection of Human-Computer Interaction (HCI) and Artificial Intelligence (AI).
Klen Čopič Pucihar and Karolina Trajkovska represented the lab and presented the poster paper “Prompt to Press: Evaluating Human Perception of AI Involvement in News Writing Across Prompt Specificity”. The work was authored by Uroš Sergaš and Marko Tkalčič, who were unable to attend in person.
Beyond presenting research, Klen chaired the “Novel Interaction (AR/VR, Embodied)” sessions, while Karolina served as a student volunteer and chaired the “Learning through Interaction” session.
Poster paper: Prompt to Press: Evaluating Human Perception of AI Involvement in News Writing Across Prompt Specificity (paper)
Abstract:
Large language models (LLMs) are becoming a common feature in content creation tools, prompting important questions about how design choices influence user trust and engagement in AIassisted journalism. Beyond output quality, factors such as prompt specificity, model choice, and authorship disclosure are themselves interaction design parameters that influence how users interpret and evaluate AI contributions. Yet, little is known about how these design decisions affect reader perceptions in journalistic contexts. To address this gap, we conducted an experiment with 150 participants who evaluated news articles on the sensitive topic of assisted suicide. The articles systematically varied in authorship (human-written, AI-edited, or AI-generated), stance (pro- or antilegalization), and prompt specificity (vague, moderate, or highly detailed). Participants rated each article on engagement, subjectivity, and perceived AI involvement, and also provided open-ended justifications for their authorship judgments. Our findings show that prompt specificity and model choice significantly influence perceptions of authorship, underscoring how technical design decisions in AI tools can shape public trust in journalism.
Publication:
- Sergaš, U., Wagne, A., Kolb, T. E., Neidhardt, J., Ferwerda, B., & Tkalčič, M. (2026). Prompt to Press: Evaluating Human Perception of AI Involvement in News Writing Across Prompt Specificity. In Companion Proceedings of the 31st International Conference on Intelligent User Interfaces (pp. 89–92). Association for Computing Machinery. https://doi.org/10.1145/3742414.3795097
Follow HICUP Lab in its official channels for more updates:
For feedback regarding our media content, you may contact our Social media and web manager.