Data Dependency Inference for Industrial Code Generation Based on UML Sequence Diagrams

2025-08-05

AI Summary

Ambiguous natural language specifications in industrial-scale code generation impede accurate modeling of implicit data dependencies. Method: This paper proposes UML2Dep—a framework that (1) extends UML sequence diagrams by integrating decision tables and API specifications to explicitly represent conditional logic and architectural constraints; (2) formulates data dependency inference as a constraint satisfaction problem, synergizing large language model–based mathematical reasoning, static program analysis, and dependency pruning to construct high-fidelity data dependency graphs; and (3) enables formalism-driven code generation. Contribution/Results: UML2Dep significantly reduces semantic ambiguity and contextual complexity, thereby improving the correctness and system reliability of generated code. Empirical evaluation in service-oriented architecture scenarios demonstrates its effectiveness and practical applicability.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Infer implicit data dependencies in service-oriented architectures
• Generate code from unambiguous formal specifications instead of ambiguous NL
• Enhance reasoning accuracy for complex UML sequence diagrams

Innovation

• Enhanced UML sequence diagrams with decision tables
• Data dependency inference via constrained mathematical reasoning
• Static parsing and pruning to reduce complexity