From Specifications to Prompts: On the Future of Generative LLMs in Requirements Engineering

TL;DR

This paper discusses how generative large language models can transform Requirements Engineering through improved prompt engineering and human evaluation, emphasizing the future potential of automated RE tasks.

Contribution

It introduces the significance of precise prompt design and human evaluation in harnessing LLMs for Requirements Engineering, highlighting future research directions.

Findings

Prompt engineering is crucial for effective LLM interactions.

Human evaluation enhances the quality of RE tasks with LLMs.

Precise prompts can unlock new automation opportunities in RE.

Abstract

Generative LLMs, such as GPT, have the potential to revolutionize Requirements Engineering (RE) by automating tasks in new ways. This column explores the novelties and introduces the importance of precise prompts for effective interactions. Human evaluation and prompt engineering are essential in leveraging LLM capabilities.