Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2512.05498 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915656376516608 |
|---|---|
| author | He, Xiao Chen, Ru Zhang, Zeqing Wang, Yanling Dong, Qiuyan |
| author_facet | He, Xiao Chen, Ru Zhang, Zeqing Wang, Yanling Dong, Qiuyan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05498 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Hybrid Approach for EMF Code Generation:Code Templates Meet Large Language Models He, Xiao Chen, Ru Zhang, Zeqing Wang, Yanling Dong, Qiuyan Software Engineering 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. |
| title | A Hybrid Approach for EMF Code Generation:Code Templates Meet Large Language Models |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2512.05498 |