GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency

Large language models (LLMs) are becoming more prevalent and have found a ubiquitous use in providing different forms of writing assistance. However, LLM-powered writing systems can frustrate users due to their limited personalization and control, which can be exacerbated when users lack experience with prompt engineering. We see design as one way to address these challenges and introduce GhostWriter, an AI-enhanced writing design probe where users can exercise enhanced agency and personalization. GhostWriter leverages LLMs to learn the user’s intended writing style implicitly as they write, while allowing explicit teaching moments through manual style edits and annotations. We study 18 participants who use GhostWriter on two different 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. From this study, we present insights regarding people’s relationship with AI-assisted writing and offer design recommendations for future work.

Users can teach the system about their target style by writing text, directly editing the style description, or highlighting parts of a document with “likes” and “dislikes.” GhostWriter also allows users to define and refine context information.

Personalization has been extensively studied for recommender systems [3, 34, 39, 45], and we take inspiration from the idea of “natural language user profiles” [45] in our designs.