Communication Dans Un Congrès Année : 2024

Automating Data Flow Diagram Generation from User Stories Using Large Language Models

Résumé

Visual modeling, particularly Data Flow Diagrams (DFDs), plays an essential role in modern software development, aiding in the design, understanding, and communication of system structures and potential security and privacy threats. Despite their importance, the manual creation of visual models is time-consuming highlighting the need for automation in the generation of DFDs from user requirements. Automating the generation of DFDs presents a significant challenge, especially in accurately interpreting user requirements and abstracting them into correct and complete diagram elements. The complexity of this task is compounded by the need for semantic accuracy and the ability to facilitate visual editing for human intervention. This study explores the use of Large Language Models (LLMs) to automate DFD generation, utilizing GPT-3.5, GPT-4, Llama2, and Mixtral models. This study emphasizes human oversight and employs an open-source diagramming tool to ensure that diagrams are accurate, complete, and editable. The findings reveal GPT-4's superior capability in generating complete DFDs, with significant progress from open-source models like Mixtral, indicating a viable path toward automated visual modeling. This approach advances scalable automation in creating visual software models, with broader implications for automating other diagram types.

Fichier principal
Vignette du fichier
Generating_Data_Flow_Diagram_with_LLM-4.pdf (714.51 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04525925 , version 1 (29-03-2024)

Licence

Identifiants

  • HAL Id : hal-04525925 , version 1

Citer

Guntur Budi Herwanto. Automating Data Flow Diagram Generation from User Stories Using Large Language Models. 7th Workshop on Natural Language Processing for Requirements Engineering, Apr 2024, Winterthur, Switzerland. ⟨hal-04525925⟩
1229 Consultations
1571 Téléchargements

Partager

  • More