Impromptu: a framework for model-driven prompt engineering

作     者：Morales, Sergio Clariso, Robert Cabot, Jordi 

作者机构：Univ Oberta Catalunya Barcelona Spain Luxembourg Inst Sci & Technol Esch Sur Alzette Luxembourg Univ Luxembourg Esch Sur Alzette Luxembourg 

出 版 物：《SOFTWARE AND SYSTEMS MODELING》 (Softw. Syst. Model.)

年 卷 期：2025年

页      面：1-19页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Fonds National de la Recherche Luxembourg [PID2020-114615RB-I00/AEI/10.13039/501100011033] Spanish government [101007260, 101007350] ECSEL Joint Undertaking (JU) Luxembourg National Research Fund (FNR) PEARL program 

主　　题：Prompt engineering Model-driven engineering Domain-specific language Generative AI Large language models 

摘      要：Generative artificial intelligence (AI) systems are capable of synthesizing complex artifacts such as text, source code or images according to the instructions provided in a natural language prompt. The quality of the input prompt, in terms of both content and structure, has a large impact on the quality of the output. This has given rise to prompt engineering, the process of designing natural language prompts to best take advantage of the capabilities of generative AI systems. This paper describes Impromptu, a model-driven engineering framework to support the creation, management and reuse of prompts for generative AI. Impromptu offers a domain-specific language (DSL) to define multimodal prompts in a modular and tool-independent way. The language offers additional features such as versioning, prompt chaining and multi-language support. Moreover, it provides tool support to adapt prompts for specific generative AI systems, execute those prompts on a generative AI system and validate the quality of the response that is generated. Impromptu is available as a Langium-based Visual Studio Code plugin.