arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.01055cs.HCcs.AIcs.CY
收藏

迈向与 AI 共同实现完整作者身份:用 AI 生成的视图支持修订

Towards Full Authorship with AI: Supporting Revision with AI-Generated Views

Calvin University(卡尔文大学)

Jiho Kim, Ray C. Flanagan, Noelle E. Haviland, ZeAi Sun, Souad N. Yakubu, Edom A. Maru, Kenneth C. Arnold

AI总结:

本文提出 Textfocals 原型,通过侧边栏中的 LLM 摘要、问题与建议引导用户反思和自主修订,在不直接生成文本的情况下维护完整作者身份。

摘要:

大型语言模型(LLM)正在通过让用户借助提示生成文本,塑造写作工具中一种新的用户界面(UI)范式。这种范式将部分创造性控制权从用户转移给系统,从而削弱用户在写作过程中的作者身份与自主性。为恢复自主性,我们提出 Textfocals,这是一个 UI 原型,旨在探究一种以人为中心、强调用户在写作中作用的方法。Textfocals 通过在文本编辑器侧边栏提供 LLM 生成的摘要、问题和建议(即 LLM 视图)来支持写作过程,鼓励写作中的反思和自主修订,而不直接生成文本。Textfocals 的 UI 可供性,包括情境自适应视图以及用于提示选择和定制的支架,提供了一种与 LLM 交互的新方式,使用户能够保持其写作的完整作者身份。一项针对 Textfocals 的形成性用户研究显示出有前景的证据,表明该方法可能帮助用户发展不成熟的想法、迎合修辞性受众并澄清其写作。然而,研究也揭示了与文档导航和范围界定、提示工程以及上下文管理相关的交互设计挑战。我们的工作强调了由生成式 AI 驱动、并保持作者身份完整性的写作支持界面所具有的广阔设计空间。

英文摘要:

Large language models (LLMs) are shaping a new user interface (UI) paradigm in writing tools by enabling users to generate text through prompts. This paradigm shifts some creative control from the user to the system, thereby diminishing the user's authorship and autonomy in the writing process. To restore autonomy, we introduce Textfocals, a UI prototype designed to investigate a human-centered approach that emphasizes the user's role in writing. Textfocals supports the writing process by providing LLM-generated summaries, questions, and advice (i.e., LLM views) in a sidebar of a text editor, encouraging reflection and self-driven revision in writing without direct text generation. Textfocals' UI affordances, including contextually adaptive views and scaffolding for prompt selection and customization, offer a novel way to interact with LLMs where users maintain full authorship of their writing. A formative user study with Textfocals showed promising evidence that this approach might help users develop underdeveloped ideas, cater to the rhetorical audience, and clarify their writing. However, the study also showed interaction design challenges related to document navigation and scoping, prompt engineering, and context management. Our work highlights the breadth of the design space of writing support interfaces powered by generative AI that maintain authorship integrity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑