ClarifyGPT: A Framework for Enhancing LLM-Based Code Generation via Requirements Clarification
Proceedings of the ACM on Software Engineering · 12.07.2024 · 1 (FSE) · 2332-2354
DOI: 10.1145/3660810 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 12.07.2024. Verfasst von Fangwen Mu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 96-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Youth Innovation Promotion Association Chinese Academy of Sciences, Basic Research Program of ISCAS, Major Program of ISCAS, National Natural Science Foundation of China.
Abstract (Originalsprache)
Large Language Models (LLMs), such as ChatGPT, have demonstrated impressive capabilities in automatically generating code from provided natural language requirements. However, in real-world practice, it is inevitable that the requirements written by users might be ambiguous or insufficient. Current LLMs will directly generate programs according to those unclear requirements, regardless of interactive clarification, which will likely deviate from the original user intents. To bridge that gap, we introduce a novel framework named C larify GPT, which aims to enhance code generation by empowering LLMs with the ability to identify ambiguous requirements and ask targeted clarifying questions. Specifically, C larify GPT first detects whether a given requirement is ambiguous by performing a code consistency check. If it is ambiguous, C larify GPT prompts an LLM to generate targeted clarifying questions. After receiving question responses, C larify GPT refines the ambiguous requirement and inputs it into the same LLM to generate a final code solution. To evaluate our C larify GPT, we invite ten participants to use C larify GPT for code generation on two benchmarks: MBPP-sanitized and MBPP-ET. The results show that C larify GPT elevates the performance (Pass@1) of GPT-4 from 70.96% to 80.80% on MBPP-sanitized. Furthermore, to conduct large-scale automated evaluations of C larify GPT across different LLMs and benchmarks without requiring user participation, we introduce a high-fidelity simulation method to simulate user responses. The results demonstrate that C larify GPT can significantly enhance code generation performance compared to the baselines. In particular, C larify GPT improves the average performance of GPT-4 and ChatGPT across five benchmarks from 62.43% to 69.60% and from 54.32% to 62.37%, respectively. A human evaluation also confirms the effectiveness of C larify GPT in detecting ambiguous requirements and generating high-quality clarifying questions. We believe that C larify GPT can effectively facilitate the practical application of LLMs in real-world development environments.
Förderung
- Youth Innovation Promotion Association Chinese Academy of Sciences, Basic Research Program of ISCAS
- Major Program of ISCAS
- National Natural Science Foundation of China
Zitieren
APA
Mu, F., Shi, L., Wang, S., Yu, Z., Zhang, B., Wang, C., Liu, S., & Wang, Q. (2024). ClarifyGPT: A Framework for Enhancing LLM-Based Code Generation via Requirements Clarification. Proceedings of the ACM on Software Engineering, 1(FSE), 2332-2354. https://doi.org/10.1145/3660810
Vancouver
Mu F, Shi L, Wang S, Yu Z, Zhang B, Wang C, et al. ClarifyGPT: A Framework for Enhancing LLM-Based Code Generation via Requirements Clarification. Proceedings of the ACM on Software Engineering. 2024;1(FSE):2332-2354. doi:10.1145/3660810
BibTeX
@article{Mu2024,
author = {Mu, Fangwen and Shi, Lin and Wang, Song and Yu, Zhuohao and Zhang, Binquan and Wang, ChenXue and Liu, Shichao and Wang, Qing},
title = {ClarifyGPT: A Framework for Enhancing LLM-Based Code Generation via Requirements Clarification},
journal = {Proceedings of the ACM on Software Engineering},
year = {2024},
volume = {1},
number = {FSE},
pages = {2332--2354},
doi = {10.1145/3660810}
}
EUVIMED