Publications

* denotes equal contribution

2026

  1. TOSEM
    A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Code Smell Detection
    Beiqi Zhang, Peng Liang, Xin Zhou, Xiyu Zhou, David Lo, Qiong Feng, Zengyang Li, and Lin Li
    ACM Transactions on Software Engineering and Methodology, 2026

2025

  1. TOSEM
    Using LLMs in generating design rationale for software architecture decisions
    Xiyu Zhou, Ruiyin Li, Peng Liang, Beiqi Zhang, Mojtaba Shahin, Zengyang Li, and Chen Yang
    ACM Transactions on Software Engineering and Methodology, 2025
  2. IST
    Architecture decisions in quantum software systems: An empirical study on Stack Exchange and GitHub
    Mst Shamima Aktar, Peng Liang, Muhammad Waseem, Amjed Tahir, Aakash Ahmad, Beiqi Zhang, and Zengyang Li
    Information and Software Technology, 2025
  3. arXiv
    Lessleak-bench: A first investigation of data leakage in llms across 83 software engineering benchmarks
    Xin Zhou, Martin Weyssow, Ratnadira Widyasari, Ting Zhang, Junda He, Yunbo Lyu, Jianming Chang, Beiqi Zhang, Dan Huang, and David Lo
    arXiv preprint arXiv:2502.06215, 2025
  4. JSS
    Exploring the problems, their causes and solutions of AI pair programming: A study on GitHub and Stack Overflow
    Xiyu Zhou, Peng Liang, Beiqi Zhang, Zengyang Li, Aakash Ahmad, Mojtaba Shahin, and Muhammad Waseem
    Journal of Systems and Software, 2025

2024

  1. EMSE
    Demystifying code snippets in code reviews: a study of the OpenStack and Qt communities and a practitioner survey
    Beiqi Zhang, Liming Fu, Peng Liang, Jiaxin Yu, and Chong Wang
    Empirical Software Engineering, 2024
  2. ASE
    Copilot-in-the-loop: Fixing code smells in copilot-generated python code using copilot
    Beiqi Zhang, Peng Liang, Qiong Feng, Yujia Fu, and Zengyang Li
    In Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering, 2024

2023

  1. SEKE
    Practices and challenges of using github copilot: An empirical study
    Beiqi Zhang, Peng Liang, Xiyu Zhou, Aakash Ahmad, and Muhammad Waseem
    In Proceedings of the 35th International Conference on Software Engineering and Knowledge Engineering, 2023
    🏆 Best Paper Award: First Place
  2. IJSEKE
    Demystifying practices, challenges and expected features of using GitHub Copilot
    Beiqi Zhang, Peng Liang, Xiyu Zhou, Aakash Ahmad, and Muhammad Waseem
    International Journal of Software Engineering and Knowledge Engineering, 2023
  3. IST
    RoseMatcher: Identifying the impact of user reviews on app updates
    Tianyang Liu, Chong Wang, Kun Huang, Peng Liang, Beiqi Zhang, Maya Daneva, and Marten Sinderen
    Information and Software Technology, 2023
  4. SANER
    Architecture decisions in ai-based systems development: An empirical study
    Beiqi Zhang, Tianyang Liu, Peng Liang, Chong Wang, Mojtaba Shahin, and Jiaxin Yu
    In 2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2023

2022

  1. ICPC
    Understanding code snippets in code reviews: A preliminary study of the openstack community
    Liming Fu, Peng Liang, and Beiqi Zhang
    In Proceedings of the 30th IEEE/ACM International Conference on Program Comprehension, 2022