{"id":2922,"date":"2026-07-20T11:59:24","date_gmt":"2026-07-20T11:59:24","guid":{"rendered":"https:\/\/hicup.famnit.upr.si\/?p=2922"},"modified":"2026-10-29T13:29:11","modified_gmt":"2026-10-29T13:29:11","slug":"hicup-lab-at-iui-2026","status":"publish","type":"post","link":"https:\/\/hicup.famnit.upr.si\/index.php\/2026\/07\/20\/hicup-lab-at-iui-2026\/","title":{"rendered":"HICUP Lab at IUI 2026"},"content":{"rendered":"\n

From July 13 to July 16, 2026, the 31st Annual ACM Conference on Intelligent User Interfaces (IUI 2026<\/a>) took place at the St Raphael Resort & Marina in Limassol, Cyprus. As a premier international venue ranked ‘A<\/em>‘ according to ICORE<\/a>, the ACM IUI conference brings together researchers and practitioners at the intersection of Human-Computer Interaction (HCI) and Artificial Intelligence (AI).\u00a0<\/p>\n\n\n\n

Klen \u010copi\u010d Pucihar<\/a> and Karolina Trajkovska<\/a> represented the lab and presented the poster paper \u201cPrompt to Press: Evaluating Human Perception of AI Involvement in News Writing Across Prompt Specificity<\/a>\u201d.<\/em> The work was authored by Uro\u0161 Serga\u0161<\/a> and Marko Tkal\u010di\u010d<\/a>, who were unable to attend in person.<\/p>\n\n\n\n

\n
\n
\"\"<\/figure>\n<\/div>\n\n\n\n
\n
\"\"<\/figure>\n<\/div>\n<\/div>\n\n\n\n
\n
\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n<\/figure>\n\n\n\n

Beyond presenting research, Klen chaired the \u201cNovel Interaction (AR\/VR, Embodied)\u201d sessions, while Karolina served as a student volunteer and chaired the \u201cLearning through Interaction\u201d session.<\/p>\n\n\n\n

\n
\n
\"\"<\/figure>\n<\/div>\n\n\n\n
\n
\"\"<\/figure>\n<\/div>\n<\/div>\n\n\n\n

Poster paper:<\/strong> Prompt to Press: Evaluating Human Perception of AI Involvement in News Writing Across Prompt Specificity<\/em> (paper<\/a>)<\/p>\n\n\n\n

Abstract:\u00a0
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.\u00a0<\/em><\/p>\n\n\n\n

Publication:<\/strong><\/p>\n\n\n\n