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 2401.14447cs.HCcs.AIcs.CLcs.LG
收藏

Wordflow:面向大语言模型的社会化提示工程

Wordflow: Social Prompt Engineering for Large Language Models

Georgia Tech(佐治亚理工学院)

Zijie J. Wang, Aishwarya Chakravarthy, David Munechika, Duen Horng Chau

AI总结:

针对非专业人士难以开展提示工程的问题,研究提出社会化提示工程范式,并开发开源社会化文本编辑器Wordflow,支持普通用户协作设计、分享提示词及本地私密运行大语言模型,助力提升非专业用户与大语言模型的交互体验。

摘要:

大语言模型(LLM)需要精心设计的提示词才能实现有效使用。提示工程即设计提示词的过程,颇具挑战性,对不太熟悉AI技术的非专业人士而言尤其如此。尽管研究人员已提出多种技术与工具来辅助LLM用户设计提示词,但这些工作主要面向AI应用开发者,而非非专业用户。为填补这一研究空白,我们提出社会化提示工程,这是一种利用社会计算技术促进协作式提示词设计的全新范式。为研究社会化提示工程,我们推出了Wordflow——一款开源的社会化文本编辑器,普通用户可借助它轻松创建、运行、分享和发现LLM提示词。此外,依托现代网络技术,Wordflow支持用户在浏览器中本地且私密地运行LLM。两个使用场景展现了社会化提示工程及我们的工具如何提升普通用户与LLM的交互体验。Wordflow可通过https://poloclub.github.io/wordflow公开访问。

英文摘要:

Large language models (LLMs) require well-crafted prompts for effective use. Prompt engineering, the process of designing prompts, is challenging, particularly for non-experts who are less familiar with AI technologies. While researchers have proposed techniques and tools to assist LLM users in prompt design, these works primarily target AI application developers rather than non-experts. To address this research gap, we propose social prompt engineering, a novel paradigm that leverages social computing techniques to facilitate collaborative prompt design. To investigate social prompt engineering, we introduce Wordflow, an open-source and social text editor that enables everyday users to easily create, run, share, and discover LLM prompts. Additionally, by leveraging modern web technologies, Wordflow allows users to run LLMs locally and privately in their browsers. Two usage scenarios highlight how social prompt engineering and our tool can enhance laypeople's interaction with LLMs. Wordflow is publicly accessible at https://poloclub.github.io/wordflow.

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。

↑