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 2304.08103cs.CLcs.HC
收藏

低代码LLM:基于大型语言模型的图形用户界面

Low-code LLM: Graphical User Interface over Large Language Models

Microsoft Research Asia(微软亚洲研究院)

Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, Wang You, Ting Song, Yan Xia, Jonathan Tien, Nan Duan, Furu Wei

AI总结:

本文提出Low-code LLM框架,通过六种低代码可视化编程交互和Planning/Executing双LLM架构,使用户无需编写复杂提示词即可可控地完成复杂任务,并通过四个典型应用验证其有效性。

摘要:

利用大型语言模型(LLMs)处理复杂任务具有挑战性,通常涉及耗时且不可控的提示工程过程。本文提出了一种新颖的人机-LLM交互框架——Low-code LLM。它融合了六种简单的低代码可视化编程交互方式,以实现更可控、更稳定的响应。通过图形用户界面的可视化交互,用户可以将自己的想法融入流程中,而无需编写琐碎的提示词。所提出的Low-code LLM框架由一个Planning LLM和一个Executing LLM组成:Planning LLM为复杂任务设计结构化的规划工作流,用户可以通过低代码可视化编程操作对其进行相应编辑和确认;Executing LLM则按照用户确认的工作流生成响应。我们强调低代码LLM的三个优势:用户友好的交互、可控的生成以及广泛的适用性。我们通过四个典型应用展示了其优势。通过引入该框架,我们旨在弥合人类与LLMs之间的差距,使LLMs能够更有效、更高效地用于复杂任务。代码、提示词和实验细节可在https://github.com/moymix/TaskMatrix/tree/main/LowCodeLLM获取。系统演示视频可在https://www.youtube.com/watch?v=jb2C1vaeO3E找到。

英文摘要:

Utilizing Large Language Models (LLMs) for complex tasks is challenging, often involving a time-consuming and uncontrollable prompt engineering process. This paper introduces a novel human-LLM interaction framework, Low-code LLM. It incorporates six types of simple low-code visual programming interactions to achieve more controllable and stable responses. Through visual interaction with a graphical user interface, users can incorporate their ideas into the process without writing trivial prompts. The proposed Low-code LLM framework consists of a Planning LLM that designs a structured planning workflow for complex tasks, which can be correspondingly edited and confirmed by users through low-code visual programming operations, and an Executing LLM that generates responses following the user-confirmed workflow. We highlight three advantages of the low-code LLM: user-friendly interaction, controllable generation, and wide applicability. We demonstrate its benefits using four typical applications. By introducing this framework, we aim to bridge the gap between humans and LLMs, enabling more effective and efficient utilization of LLMs for complex tasks. The code, prompts, and experimental details are available at https://github.com/moymix/TaskMatrix/tree/main/LowCodeLLM. A system demonstration video can be found at https://www.youtube.com/watch?v=jb2C1vaeO3E.

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。

↑