GhostWriter：通过个性化和代理，增强协作人工智能写作体验

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

February 13, 2024

作者: Catherine Yeh, Gonzalo Ramos, Rachel Ng, Andy Huntington, Richard Banks

cs.AI

摘要

大型语言模型（LLMs）正变得更加普遍，并已在提供不同形式的写作辅助方面得到广泛应用。然而，由于个性化和控制方面的局限性，LLM驱动的写作系统可能会让用户感到沮丧，尤其是当用户缺乏提示工程经验时，这种情况可能会加剧。我们认为设计是解决这些挑战的一种方式，并介绍了GhostWriter，这是一种AI增强的写作设计探针，用户可以在其中行使增强的代理权和个性化。GhostWriter利用LLMs在用户写作时隐式学习用户的预期写作风格，同时通过手动样式编辑和注释提供显式教学时刻。我们研究了18名参与者在两个不同写作任务上使用GhostWriter，观察到它有助于用户撰写个性化的文本生成，并通过提供多种控制系统写作风格的方式赋予用户权力。通过这项研究，我们提出了关于人们与AI辅助写作的关系的见解，并为未来的工作提供设计建议。

English

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.