Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process
🤖 AI Summary
The widespread adoption of generative AI poses critical challenges to authorial agency and intellectual ownership, yet its impact on the full cognitive writing process remains poorly understood. This study systematically reviews 109 HCI publications and conducts in-depth interviews with 15 interdisciplinary writers. We propose the first analytical framework for AI-supported writing, structured across four cognitive stages: planning, translating, reviewing, and monitoring. Based on empirical findings, we identify four human-centered design strategies: structured scaffolding, guided exploration, proactive co-writing, and critical feedback. We further reveal divergent agency and originality requirements between content-oriented and form-oriented writers across stages. Finally, we uncover three key research-practice mismatches and distill actionable design principles for adaptive AI writing tools—thereby advancing both theoretical understanding of writerly agency and practical pathways for context-sensitive tool development.
Application Category
📝 Abstract
As generative AI tools like ChatGPT become integral to everyday writing, critical questions arise about how to preserve writers' sense of agency and ownership when using these tools. Yet, a systematic understanding of how AI assistance affects different aspects of the writing process - and how this shapes writers' agency - remains underexplored. To address this gap, we conducted a systematic review of 109 HCI papers using the PRISMA approach. From this literature, we identify four overarching design strategies for AI writing support: structured guidance, guided exploration, active co-writing, and critical feedback - mapped across the four key cognitive processes in writing: planning, translating, reviewing, and monitoring. We complement this analysis with interviews of 15 writers across diverse domains. Our findings reveal that writers' desired levels of AI intervention vary across the writing process: content-focused writers (e.g., academics) prioritize ownership during planning, while form-focused writers (e.g., creatives) value control over translating and reviewing. Writers' preferences are also shaped by contextual goals, values, and notions of originality and authorship. By examining when ownership matters, what writers want to own, and how AI interactions shape agency, we surface both alignment and gaps between research and user needs. Our findings offer actionable design guidance for developing human-centered writing tools for co-writing with AI, on human terms.
Problem
Research questions and friction points this paper is trying to address.
How AI affects writers' agency in writing process
Design strategies for AI writing support
Writers' varying preferences for AI intervention
Innovation
Methods, ideas, or system contributions that make the work stand out.
Systematic review of 109 HCI papers
Four design strategies for AI writing support
Interviews with 15 diverse domain writers
🔎 Similar Papers
No similar papers found.
