Coauthoring support improves control and engagement in writing
CoWriter: Guiding Methodological and Synergetic Human-LLM Co-Authoring
Computation and LanguageArtificial IntelligenceHuman-Computer Interaction
Summary
Writing long, detailed texts with AI often makes people feel like they're just watching rather than truly creating, leading to tiredness and too much reliance on the AI. The authors made a tool called CoWriter that helps people stay active and involved by guiding them through proven expert writing steps. People using CoWriter felt more ownership of their text and shared their own ideas better than those using regular AI tools. Outside readers also thought texts created this way felt more personal and interesting.
What this means in practice
- •For content creation teams: Support writers in producing long, thoughtful documents by actively guiding them through writing tasks and encouraging ownership.
- •For marketing copywriters: Enable copywriters to infuse personal storytelling and unique experiences into AI-assisted drafts for more authentic brand communication.
Authors
Shmuel Amar, Benjamin Lieber, Ori Shapira, Debanjana Kar, Sebastian Maximilian Dennerlein, Yufang Hou, Ido Dagan
Abstract
While LLMs have transformed text generation, standard chat-and-canvas interfaces often reduce human authoring to quite passive supervision, causing review fatigue, over-reliance on AI, and the sidelining of the human role in long-form, source-grounded writing. Prior systems typically address isolated writing phases, leaving comprehensive end-to-end human-LLM collaboration largely unexplored. In this paper, we introduce CoWriter, a proactive agentic scheme that adapts expert human (co-)authoring methodologies from cognitive science to flexibly steer the entire writing workflow while actively encouraging the user to engage. In an exploratory user study, compared to a standard LLM baseline, authors using CoWriter better expressed their perspectives and maintained a higher sense of document ownership, supported quantitatively by $2.2\times$ more successful agent engagements. Furthermore, external reader judges rated the resulting texts higher in "human touch" qualities like storytelling and integrating unique personal experiences. Overall, our results demonstrate that proactively engaging users through established human practices is beneficial for effective LLM-supported co-authoring, providing useful methodologies, techniques and insights for future research on collaborative agents.