When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention-Reference-Cited by-同舟云学术

When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention

Published:2024-09-11 Issue: Volume:35 Page:1073-1085
ISSN:
Container-title:Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis
language:
Short-container-title:

Author:

Guo Lianghong¹^ORCID,Wang Yanlin¹^ORCID,Shi Ensheng²^ORCID,Zhong Wanjun³^ORCID,Zhang Hongyu⁴^ORCID,Chen Jiachi¹^ORCID,Zhang Ruikai⁵^ORCID,Ma Yuchi⁵^ORCID,Zheng Zibin¹^ORCID

Affiliation:

1. Sun Yat-sen University, Zhuhai city, China

2. Xi'an Jiaotong University, Xi'an city, China

3. Sun Yat-sen University, Guangzhou city, China

4. Chongqing University, Chongqing city, China

5. Huawei Cloud Computing Technologies, Shenzhen city, China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3650212.3680343

Reference68 articles.

1. Lakshya A Agrawal Aditya Kanade Navin Goyal Shuvendu K Lahiri and Sriram K Rajamani. 2023. Guiding Language Models of Code with Global Context using Monitors. arXiv preprint arXiv:2306.10763.

2. Deep Software Analytics. 2024. CodeFast. https://github.com/DeepSoftwareAnalytics/CodeFast

3. Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Uddin Ahmad, Shiqi Wang, Qing Sun, and Mingyue Shang. 2022. Multi-lingual Evaluation of Code Generation Models. In The Eleventh International Conference on Learning Representations.

4. Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry and Quoc Le. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732.

5. Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade, Arun Iyer, Suresh Parthasarathy, Sriram Rajamani, B Ashok, and Shashank Shet. 2024. Codeplan: Repository-level coding using llms and planning. Proceedings of the ACM on Software Engineering, 1, FSE (2024), 675–698.