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

TL;DR

This paper presents Low-code LLM, a graphical user interface framework that simplifies human-LLM interaction, making complex task execution more controllable, stable, and accessible without extensive prompt engineering.

Contribution

It introduces a novel low-code visual programming framework for LLMs, enabling user-friendly, controllable, and wide-applicability interactions for complex tasks.

Findings

Enhanced user control over LLM responses

Reduced prompt engineering complexity

Effective application across four typical tasks

Abstract

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.