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.
@article{arxiv.2403.13583,
title = {CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing},
author = {Xinyi He and Jiaru Zou and Yun Lin and Mengyu Zhou and Shi Han and Zejian Yuan and Dongmei Zhang},
journal= {arXiv preprint arXiv:2403.13583},
year = {2024}
}
Comments
Accepted by EMNLP 2024 main conference, long paper