With AI automating consequential tasks, human oversight is required for ethical, legal, and practical reasons. Yet these oversight tasks can be demanding and often make for poor work. Empirical evidence on overseers'lived work experiences remains underexplored, yet critical for designing ``good''oversight. We provide l...
Cedric Faas, Lisa Dargasz, Julius Gabelmann et al.· 0 citations
This work investigated post-task workflows: editable, graph-based representations of an agent's completed execution that improve their understanding and error detection over a prompt-only condition, and found that validation succeeded mainly when users cross-checked across multiple evidence sources.
Ze-Kun Wu, Xin-Ru Wang, R. Pang et al.· 0 citations
Ollie is introduced, a gaze-informed proactive artificial intelligence (AI) assistant that offers short narrative descriptions based on where a child is looking that shows the feasibility of using gaze as an implicit input for proactive AI assistance for children and provides design implications for future child-center...
Ze-Kun Wu, Man Su, Huiyong Li et al.· arXiv.org· 0 citations
The qualitative analysis reveals the factors users consider in their anchoring decision, including interface accessibility, stability during interaction, visual clutter, and individual mental models, which inform the design of adaptive and controllable MR interfaces and highlight the importance of supporting user custo...
J. Belo, Sina Elahimanesh, A. Feit· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.