CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917801114992640 |
|---|---|
| author | He, Xinyi Zou, Jiaru Lin, Yun Zhou, Mengyu Han, Shi Yuan, Zejian Zhang, Dongmei |
| author_facet | He, Xinyi Zou, Jiaru Lin, Yun Zhou, Mengyu Han, Shi Yuan, Zejian Zhang, Dongmei |
| contents | Large Language Models have revolutionized code generation ability by converting natural language descriptions into executable code. However, generating complex code within real-world scenarios remains challenging due to intricate structures, subtle bugs, understanding of advanced data types, and lack of supplementary contents. To address these challenges, we introduce the CoCoST framework, which enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement. Moreover, CoCoST serializes the complex inputs and outputs to improve comprehension and generates test cases to ensure the adaptability for real-world applications. CoCoST is validated through rigorous experiments on the DS-1000 and ClassEval datasets. Experimental results show that CoCoST substantially improves the quality of complex code generation, highlighting its potential to enhance the practicality of LLMs in generating complex code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13583 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing He, Xinyi Zou, Jiaru Lin, Yun Zhou, Mengyu Han, Shi Yuan, Zejian Zhang, Dongmei Software Engineering Computation and Language Machine Learning Large Language Models have revolutionized code generation ability by converting natural language descriptions into executable code. However, generating complex code within real-world scenarios remains challenging due to intricate structures, subtle bugs, understanding of advanced data types, and lack of supplementary contents. To address these challenges, we introduce the CoCoST framework, which enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement. Moreover, CoCoST serializes the complex inputs and outputs to improve comprehension and generates test cases to ensure the adaptability for real-world applications. CoCoST is validated through rigorous experiments on the DS-1000 and ClassEval datasets. Experimental results show that CoCoST substantially improves the quality of complex code generation, highlighting its potential to enhance the practicality of LLMs in generating complex code. |
| title | CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing |
| topic | Software Engineering Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2403.13583 |