Ai.llude: Encouraging Rewriting AI-Generated Text to Support Creative Expression
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2024.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 1; 2025: 5; 2026: 3.
9 papers.
- 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Editscited by 49
- 2025Phraselette: A Poet's Procedural Palettecited by 4
- 2025Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agentscited by 4
- 2025AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professionscited by 3
- 2025Scaffolding Recursive Divergence and Convergence in Story Ideationcited by 2
- 2025CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detectioncited by 0
- 2026Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativitycited by 0
- 2026Beyond Compliance: How AI Could Help Creative Writers by Refusing Themcited by 0
- 2026Language as a Material Interface for Creative LLM Interactioncited by 0
- 2026Language as a Material Interface for Creative LLM Interaction25 May 2026
- 2026Beyond Compliance: How AI Could Help Creative Writers by Refusing Them3 Apr 2026
- 2026Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativity10 Mar 2026
- 2025CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection16 Aug 2025
- 2025Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agents8 Jul 2025
- 2025Scaffolding Recursive Divergence and Convergence in Story Ideation4 Jul 2025
- 2025AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professions12 Mar 2025
- 2025Phraselette: A Poet's Procedural Palette8 Mar 2025
- 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits22 Sep 2024