Technology Category
Natural Language Processing: Prompt Engineering / PromptingMachine Learning: Large Multimodal Models (LMMs)Humans and AI: Game Design — Procedural Content Generation & Storytelling
Exploring LLMs for User Story Extraction from Mockups
🤖 AI Summary
This study addresses a key challenge in agile software development: the efficient and accurate extraction of user stories from high-fidelity prototype mockups. To tackle this, the authors propose a novel approach that integrates a Language Extension Lexicon (LEL) into prompt engineering for large language models (LLMs), thereby guiding the model to better interpret UI elements and generate higher-quality user stories. This work represents the first effort to incorporate LEL into LLM prompt design, significantly enhancing the accuracy and applicability of the generated content. Experimental results demonstrate that the proposed method substantially outperforms baseline approaches without LEL in terms of user story quality, thereby facilitating more effective requirements communication between developers and stakeholders.
Technology Category
Application Category
📝 Abstract
User stories are one of the most widely used artifacts in the software industry to define functional requirements. In parallel, the use of high-fidelity mockups facilitates end-user participation in defining their needs. In this work, we explore how combining these techniques with large language models (LLMs) enables agile and automated generation of user stories from mockups. To this end, we present a case study that analyzes the ability of LLMs to extract user stories from high-fidelity mockups, both with and without the inclusion of a glossary of the Language Extended Lexicon (LEL) in the prompts. Our results demonstrate that incorporating the LEL significantly enhances the accuracy and suitability of the generated user stories. This approach represents a step forward in the integration of AI into requirements engineering, with the potential to improve communication between users and developers.
Problem
Research questions and friction points this paper is trying to address.
user story extraction
mockups
requirements engineering
large language models
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large Language Models
User Story Extraction
High-Fidelity Mockups
Language Extended Lexicon
Requirements Engineering
🔎 Similar Papers
No similar papers found.
