GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency
This work addresses the need for better user agency and personalization in AI-assisted writing tools, particularly for non-experts, though it is incremental as it builds on existing LLM systems with design improvements.
The authors tackled the problem of LLM-powered writing systems lacking personalization and control for users, especially those inexperienced with prompt engineering, by introducing GhostWriter, which helped 18 participants craft personalized text and provided multiple ways to control writing style in two distinct tasks.
Large language models (LLMs) have become ubiquitous in providing different forms of writing assistance to different writers. However, LLM-powered writing systems often fall short in capturing the nuanced personalization and control needed to effectively support users -- particularly for those who lack experience with prompt engineering. To address these challenges, we introduce GhostWriter, an AI-enhanced design probe that enables users to exercise enhanced agency and personalization during writing. GhostWriter leverages LLMs to implicitly learn the user's intended writing style for seamless personalization, while exposing explicit teaching moments for style refinement and reflection. We study 18 participants who use GhostWriter on two distinct writing tasks, observing that it helps users craft personalized text generations and empowers them by providing multiple ways to control the system's writing style. Based on this study, we present insights on how specific design choices can promote greater user agency in AI-assisted writing and discuss people's evolving relationships with such systems. We conclude by offering design recommendations for future work.