Document Type
Presentation
Publication Title
Proceedings of the Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing), NAACL 2025
Abstract
This paper explores interaction designs for gen-
erative AI interfaces that necessitate human in-
volvement 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 interac-
tion techniques: (1) using a predictive-text in-
teraction to type the assistant’s response to a
revision request, and (2) highlighting potential
edit opportunities in a document. Our imple-
mentations demonstrate how these approaches
reveal the landscape of writing possibilities and
enable fine-grained control. We discuss impli-
cations for human-AI writing partnerships and
future interaction design directions.
First Page
1
Last Page
7
DOI
https://doi.org/10.18653/v1/2025.in2writing-1.6
Publication Date
5-4-2025
Recommended Citation
Arnold, Kenneth C.; Kim, Jiho; Chew, Jason G.; Yoo, Jooha; Kim, Juyeong; Flanagan, Ray; and Kwon, Heonjae, "Interaction-Required Suggestions for Control, Ownership, and Awareness in Human-AI Co-Writing" (2025). University Faculty Publications and Creative Works. 984.
https://digitalcommons.calvin.edu/calvin_facultypubs/984