
Insights into Mixed-Initiative User Interfaces and Human-AI Collaboration
Explore the principles of mixed-initiative user interfaces, relevance to current research, and perspectives on interface agents from Lucy and Simon. Discover the importance of combining human intuition with computational assistance for better outcomes in collaborative approaches. Learn how projects can leverage these insights to enhance user experience and refine results through efficient agent-user collaboration.
Download Presentation

Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Principles of Mixed-Initiative User Interfaces Eric Horvitz Microsoft Research Discussant: Yi Wen 27th Sep
Relevance to todays research Interface agents that provide automation various tasks AI agents that understand natural language to execute Might make poor guesses about users less likely to have error
Mixed initiative user interface Human-AI collaboration
Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs Xu Wang et.al. NAACL 2022 Xu Wang Simin Fan Jessica Houghton Lu Wang
What Lucy has said about this research? Lucy s viewpoint on interface agent: They can oversimplify complex human interactions and decision-making processes Importance of understanding the context in which technology is used Systems should support human interaction rather than replace it A more collaborative approach, where technology assists and augments human activity rather than attempting to act independently
What Simon has said about this research? Bounded rationality of human beings importance of combining human intuition with computational assistance to achieve better outcomes
How projects might learn from these results Considering the status of a user s attention in the timing of services. Maintaining working memory of recent interactions. Providing mechanisms for efficient agent-user collaboration to refine results.