Interaction-Required Suggestions for Control, Ownership, and Awareness in Human-AI Co-Writing
By: Kenneth C. Arnold, Jiho Kim
Potential Business Impact:
Helps people write better with smart computer help.
This paper explores interaction designs for generative AI interfaces that necessitate human involvement throughout the generation process. We argue that such interfaces can promote cognitive engagement, agency, and thoughtful decision-making. Through a case study in text revision, we present and analyze two interaction techniques: (1) using a predictive-text interaction to type the assistant's response to a revision request, and (2) highlighting potential edit opportunities in a document. Our implementations demonstrate how these approaches reveal the landscape of writing possibilities and enable fine-grained control. We discuss implications for human-AI writing partnerships and future interaction design directions.
Similar Papers
Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
Human-Computer Interaction
Helps writers keep control when using AI.
Interaction-Augmented Instruction: Modeling the Synergy of Prompts and Interactions in Human-GenAI Collaboration
Human-Computer Interaction
Helps AI understand instructions better with clicks.
How Problematic Writer-AI Interactions (Rather than Problematic AI) Hinder Writers' Idea Generation
Human-Computer Interaction
AI helps students learn better when they think.