Data Dependency-Aware Code Generation from Enhanced UML Sequence Diagrams

TL;DR

This paper presents UML2Dep, a framework that enhances UML sequence diagrams with formal specifications and data dependency inference to improve code generation accuracy from complex service-oriented architecture requirements.

Contribution

It introduces an extended UML diagram with decision tables and API specs, and a data dependency inference task formalized for LLMs, advancing code synthesis from detailed formal specifications.

Findings

Explicit data dependency graphs improve code accuracy.

Formalized DDI aligns with LLM reasoning strengths.

Static parsing reduces complexity and enhances reliability.

Abstract

Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors, conditional logic, and architectural constraints; implicit data dependencies in service-oriented architectures are difficult to infer and handle correctly. To bridge this gap, we propose a novel step-by-step code generation framework named UML2Dep by leveraging unambiguous formal specifications of complex requirements. First, we introduce an enhanced Unified Modeling Language (UML) sequence diagram tailored for service-oriented architectures. This diagram extends traditional visual syntax by integrating decision tables and API specifications, explicitly formalizing structural relationships and business logic flows in service interactions to rigorously eliminate linguistic ambiguity. Second, recognizing the critical role of data flow, we introduce a dedicated data dependency inference (DDI) task. DDI systematically constructs an explicit data dependency graph prior to actual code synthesis. To ensure reliability, we formalize DDI as a constrained mathematical reasoning task through novel prompting strategies, aligning with LLMs' excellent mathematical strengths. Additional static parsing and dependency pruning further reduce context complexity and cognitive load associated with intricate specifications, thereby enhancing reasoning accuracy and efficiency.