A Hybrid Approach for EMF Code Generation:Code Templates Meet Large Language Models

TL;DR

This paper introduces iEcoreGen, a hybrid system combining EMF templates and large language models to improve automated Java code generation, balancing correctness and flexibility.

Contribution

It presents a novel hybrid approach integrating EMF and LLMs for code generation, demonstrating improved accuracy over LLM-only methods.

Findings

Outperforms LLM-only baselines on pass@k metrics

Achieves comparable results to LLMs on compilation@k

Ablation study shows the importance of each component

Abstract

Template-based and LLM-based code generation are both key enablers of automated software development. The former provides correctness guarantees but are rigid for complex requirements, whereas LLMs offer high flexibility at the risk of producing faulty code.This paper proposes iEcoreGen, a hybrid approach that integrates Eclipse Modeling Framework (EMF) and LLMs. In EMF, an Ecore model defines a system structure and acts as a blueprint for code-generation.iEcoreGen decomposes requirements to derive operation specifications, uses EMF's template-based generator to produce initial Java code, and serializes specifications into docstrings. LLMs are then invoked to complete and fix unimplemented methods. We assessed iEcoreGen on twenty code-generation tasks across five LLMs. It surpasses LLM-only baselines on pass@k and performs on par with them on compilation@k. An ablation study clarified the contribution of each component of iEcoreGen. Overall, the findings indicate that LLM-enhanced model-driven development is a promising path toward more efficient software automation.