Ai.llude: Encouraging Rewriting AI-Generated Text to Support Creative Expression
David Zhou, Sarah Sterman

TL;DR
Ai.llude proposes a method to encourage rewriting of AI-generated text by deliberately providing imperfect suggestions, aiming to enhance creative ownership and decision-making in the writing process.
Contribution
This work introduces a novel approach of using imperfect AI suggestions to motivate rewriting, fostering greater engagement and ownership in creative writing.
Findings
Intermediate suggestions significantly motivate rewriting
Writers adapt and revise AI suggestions more when suggestions are imperfect
Implications for designing AI writing support tools
Abstract
In each step of the creative writing process, writers must grapple with their creative goals and individual perspectives. This process affects the writer's sense of authenticity and their engagement with the written output. Fluent text generation by AIs risks undermining the reflective loop of rewriting. We hypothesize that deliberately generating imperfect intermediate text can encourage rewriting and prompt higher level decision making. Using logs from 27 writing sessions using a text generation AI, we characterize how writers adapt and rewrite AI suggestions, and show that intermediate suggestions significantly motivate and increase rewriting. We discuss the implications of this finding, and future steps for investigating how to leverage intermediate text in AI writing support tools to support ownership over creative expression.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
