ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916973792722944 |
|---|---|
| author | He, Minghua Chen, Yue Yang, Fangkai Zhao, Pu Yin, Wenjie Kang, Yu Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei |
| author_facet | He, Minghua Chen, Yue Yang, Fangkai Zhao, Pu Yin, Wenjie Kang, Yu Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei |
| contents | Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code, which results in unguaranteed code executability and unreliable automated code translation. To address this issue, we propose ExeCoder, an LLM specifically designed for code translation, aimed at utilizing executability representations such as functional semantics, syntax structures, and variable dependencies to enhance the capabilities of LLMs in code translation. To evaluate the effectiveness of ExeCoder, we manually enhanced the widely used benchmark TransCoder-test, resulting in a benchmark called TransCoder-test-X that serves LLMs. Evaluation of TransCoder-test-X indicates that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics, and even outperforms the renowned closed-source LLM GPT-4o. Code is available at https://aka.ms/execoder |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18460 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation He, Minghua Chen, Yue Yang, Fangkai Zhao, Pu Yin, Wenjie Kang, Yu Lin, Qingwei Rajmohan, Saravan Zhang, Dongmei Software Engineering Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code, which results in unguaranteed code executability and unreliable automated code translation. To address this issue, we propose ExeCoder, an LLM specifically designed for code translation, aimed at utilizing executability representations such as functional semantics, syntax structures, and variable dependencies to enhance the capabilities of LLMs in code translation. To evaluate the effectiveness of ExeCoder, we manually enhanced the widely used benchmark TransCoder-test, resulting in a benchmark called TransCoder-test-X that serves LLMs. Evaluation of TransCoder-test-X indicates that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics, and even outperforms the renowned closed-source LLM GPT-4o. Code is available at https://aka.ms/execoder |
| title | ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2501.18460 |