Reproduce “Leveraging Large Language Models for Use Case Model Generation from Software Requirements” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tobias Eisenreich, Nicholas Friedlaender, Stefan Wagner
Researchers at the Technical University of Munich developed a semi-automated method using large language models to generate use case models from software requirements. This approach reduced modeling time by approximately 60% while maintaining or improving model quality compared to manual methods, and was positively received by professional software engineers.
Key insights
- LLMs can significantly accelerate specific, structured software engineering tasks like use case modeling, serving as effective intelligent assistants rather than full automation.
- The semi-automated approach, allowing user intervention and refinement, is crucial for addressing LLM limitations such as occasional hallucinations or syntax errors and enhancing user trust.
- While developers appreciate the efficiency and quality of LLM-generated models, they identify critical needs for future tools, including enhanced reasoning, iterative dialogue capabilities, and improved traceability features.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.