Large Language Models for Automated Program Repair

被引：2
|
作者：
Ribeiro, Francisco [1 ]
机构：
[1] Univ Minho, HASLab INESC TEC, Braga, Portugal
来源：
COMPANION PROCEEDINGS OF THE 2023 ACM SIGPLAN INTERNATIONAL CONFERENCE ON SYSTEMS, PROGRAMMING, LANGUAGES, AND APPLICATIONS: SOFTWARE FOR HUMANITY, SPLASH COMPANION 2023 | 2023年
关键词：
automated program repair; fault localization; code generation; type systems;
D O I：
10.1145/3618305.3623587
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper introduces two methods for automated program repair (APR) utilizing pre-trained language models. The first method demonstrates program repair as a code completion task and is validated on a dataset of Java programs. The second method, Mentat, leverages OCaml's parser and type system as fault localization techniques to generate prompts for GPT-3, producing candidate patches. Evaluation results show promising repair rates, with 27% and 39.2% effectiveness, respectively. For OCaml, a comparative study employing an automated validation strategy is presented in which the technique outperforms other tools. Language models are effective at APR, enhancing bug fixing and freeing developers to focus on other critical aspects of software engineering.
引用
收藏
页码：7 / 9
页数：3
相关论文
共 50 条
  • [1] Large Language Models for Automated Program Repair
    Ribeiro, Francisco
    SPLASH Companion 2023 - Companion Proceedings of the 2023 ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity, 2023, : 7 - 9
  • [2] Leveraging Large Language Models for Automated Program Repair in Programming Education
    Murali, Pavithra Sripathanallur
    XRDS: Crossroads, 2025, 31 (02): : 58 - 60
  • [3] Automated Program Repair in the Era of Large Pre-trained Language Models
    Xia, Chunqiu Steven
    Wei, Yuxiang
    Zhang, Lingming
    2023 IEEE/ACM 45TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ICSE, 2023, : 1482 - 1494
  • [4] The use of large language models for program repair
    Zubair, Fida
    Al-Hitmi, Maryam
    Catal, Cagatay
    COMPUTER STANDARDS & INTERFACES, 2025, 93
  • [5] Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair
    Wei, Yuxiang
    Xia, Chunqiu Steven
    Zhang, Lingming
    PROCEEDINGS OF THE 31ST ACM JOINT MEETING EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING, ESEC/FSE 2023, 2023, : 172 - 184
  • [6] Impact of Code Language Models on Automated Program Repair
    Jiang, Nan
    Liu, Kevin
    Lutellier, Thibaud
    Tan, Lin
    2023 IEEE/ACM 45TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ICSE, 2023, : 1430 - 1442
  • [7] Automated Repair of Programs from Large Language Models
    National University of Singapore, Singapore
    不详
    不详
    arXiv, 1600,
  • [8] Automated Repair of Programs from Large Language Models
    Fan, Zhiyu
    Gao, Xiang
    Mirchev, Martin
    Roychoudhury, Abhik
    Tan, Shin Hwei
    2023 IEEE/ACM 45TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ICSE, 2023, : 1469 - 1481
  • [9] An Empirical Study on Fine-tuning Large Language Models of Code for Automated Program Repair
    Huang, Kai
    Meng, Xiangxin
    Zhang, Jian
    Liu, Yang
    Wang, Wenjie
    Li, Shuhao
    Zhang, Yuqing
    2023 38TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING, ASE, 2023, : 1162 - 1174
  • [10] Large Language Models in Automated Repair of Haskell Type Errors
    Santos, Sofia
    Saraiva, Joao
    Ribeiro, Francisco
    2024 ACM/IEEE INTERNATIONAL WORKSHOP ON AUTOMATED PROGRAM REPAIR, APR 2024, 2024, : 42 - 45
12345