PromptChainer: Chaining Large Language Model Prompts through Visual Programming
Tongshuang Wu University of WashingtonUSA , Ellen Jiang Google ResearchUSA , Aaron Donsbach Google ResearchUSA , Jeff Gray Google ResearchUSA , Alejandra Molina Google ResearchUSA , Michael Terry Google ResearchUSA and Carrie J. Cai Google ResearchUSA
Abstract
While LLMs have made it possible to rapidly prototype new ML functionalities, many real-world applications involve complex tasks that cannot be easily handled via a single run of an LLM. Recent work has found that chaining multiple LLM runs together (with the output of one step being the input to the next) can help users accomplish these more complex tasks, and in a way that is perceived to be more transparent and controllable. However, it remains unknown what users need when authoring their own LLM chains – a key step to lowering the barriers for non-AI-experts to prototype AI-infused applications. In this work, we explore the LLM chain authoring process. We find from pilot studies that users need support transforming data between steps of a chain, as well as debugging the chain at multiple granularities. To address these needs, we designed PromptChainer, an interactive interface for visually programming chains. Through case studies with four designers and developers, we show that PromptChainer supports building prototypes for a range of applications, and conclude with open questions on scaling chains to even more complex tasks, as well as supporting low-fi chain prototyping.
中文速览
大型语言模型（LLM）让非专业人士也能快速搭建AI功能原型，但现实应用往往需要多个步骤协同完成，单次调用LLM远远不够。为此，研究者开发了PromptChainer——一个可视化的"LLM链"编排工具，让用户能像搭积木一样把多个LLM调用串联成完整流程，并通过节点预览、自动同步输入输出名称、多粒度断点调试等功能，解决数据格式转换困难、提示词改动引发连锁错误等核心痛点。通过与四位设计师和开发者的案例研究，验证了该工具能支持聊天机器人、写作助手等多种真实应用的原型搭建，用户不仅用链式结构弥补单个LLM的不足，还借此让原型更易扩展和维护。这项工作为非AI专家参与复杂AI应用原型设计铺平了道路，同时也指出了未来在处理高度相互依赖的复杂任务和支持低成本快速迭代方面仍需突破的挑战。
原文 arXiv:2203.06566;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2203.06566v1