Preference-based prompting raises LLM adherence to object-oriented design principles in UML generation but leaves substantial output variance and model-specific differences intact.
A Model Is Not Built By A Single Prompt: LLM-Based Domain Modeling With Question Decomposition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 2roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Reliability of Large Language Models for Design Synthesis: An Empirical Study of Variance, Prompt Sensitivity, and Method Scaffolding
Preference-based prompting raises LLM adherence to object-oriented design principles in UML generation but leaves substantial output variance and model-specific differences intact.
- Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework