New benchmark standardizes automated domain modeling evaluation

Researchers have introduced a new benchmark to standardize the evaluation of automated domain modeling techniques. This benchmark integrates the Golden UML Modelset with a reference archive from Chen et al., providing a comprehensive dataset for assessing models that generate domain models from natural language descriptions. The benchmark is designed to facilitate the comparison of various approaches, including LLM-driven strategies, and is made available as a research artifact to promote reuse and further investigation in the field. AI

IMPACT Standardizes evaluation for domain modeling, potentially accelerating LLM-driven approaches in software engineering.

RANK_REASON The item is a research paper introducing a new benchmark for evaluating automated domain modeling techniques. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Calamotropha
• Chen
• Chue Hong
• FAIR4RS Principles
• Golden UML Modelset
• Hugging Face
• Mecella
• Snoeck
• Text2UML
• Verbruggen
• Zenodo

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →