On the Effectiveness of Training Data Optimization for LLM-based Code Generation: An Empirical Study
Published in ACM Transactions on Software Engineering and Methodology (TOSEM), 2026
Shiqi Kuang, Zhao Tian, Tao Xiao, Dong Wang, Junjie Chen [pdf]
CV
Education
Doctor of Engineering, Nara Institute of Science and Technology, Japan, 2024
Master of Engineering, Nara Institute of Science and Technology, Japan, 2022
Work Experience
- 2024 - Present: Assistant Professor
- Kyushu University, Japan
- Part of the POSL (Principles of Software engineering and programming Languages) Lab.
- 2020 - 2024: Research Assistant
- Nara Institute of Science and Technology, Japan
Publications
Recovering Revisions of Pull Requests with Altered History
Published in The 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026
Gengyi Sun, Georges Aaron Randrianaina, Tao Xiao, Yasutaka Kamei, Shane McIntosh [pdf]
How Well Do LLMs Generate Taxonomies in the SE Domain? A Multi-perspective Evaluation Framework
Published in The 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026
Sota Nakashima, Yuta Ishimoto, Masanari Kondo, Tao Xiao, Yasutaka Kamei [pdf]
ThinkLog: Leveraging Reasoning for Log Statement Generation
Published in The 26th International Conference on Software Quality, Reliability, and Security (QRS), 2026 (Short Paper)
Kazuki Kusama, Honglin Shu, Masanari Kondo, Tao Xiao, Yasutaka Kamei [pdf]
Exploring the Potential of Program Flowcharts on Code Generation Using Multimodal LLMs
Published in The 26th International Conference on Software Quality, Reliability, and Security (QRS), 2026
Yuki Toi, Tao Xiao, Kazushi Tomoto, Masanari Kondo, Yasutaka Kamei [pdf]
Cross-Project Flakiness: A Case Study of the OpenStack Ecosystem
Published in IEEE Transactions on Software Engineering (TSE), 2026
Tao Xiao, Dong Wang, Shane McIntosh, Hideaki Hata, Yasutaka Kamei [pdf]
Self-Admitted GenAI Usage in Open-Source Software
Published in IEEE Transactions on Software Engineering (TSE), 2026
Tao Xiao, Youmei Fan, Fabio Calefato, Christoph Treude, Raula Gaikovina Kula, Hideaki Hata, Sebastian Baltes [pdf]
AILINKPREVIEWER: Enhancing Code Reviews with LLM-Powered Link Previews
Published in 32nd Asia-Pacific Software Engineering Conference, 2025 (Tool Demonstration)
Panya Trakoolgerntong, Tao Xiao, Masanari Kondo, Chaiyong Ragkhitwetsagul, Morakot Choetkiertikul, Pattaraporn Sangaroonsilp, Yasutaka Kamei [pdf]
How Far Have LLMs Come Toward Automated SATD Taxonomy Construction?
Published in 32nd Asia-Pacific Software Engineering Conference, 2025 (Early Research Achievements)
Sota Nakashima, Yuta Ishimoto, Masanari Kondo, Tao Xiao, Yasutaka Kamei [pdf]
Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions
Published in The ACM International Conference on the Foundations of Software Engineering (FSE), 2024
Tao Xiao, Hideaki Hata, Christoph Treude, Kenichi Matsumoto [pdf]
How Trustworthy Is Your Continuous Integration (CI) Accelerator?: A Comparison of the Trustworthiness of CI Acceleration Products
Published in IEEE Software, 2024
Zhili Zeng, Tao Xiao, Maxime Lamothe, Hideaki Hata, Shane McIntosh [pdf]
A Mutation-Guided Assessment of Acceleration Approaches for Continuous Integration: An Empirical Study of YourBase
Published in 21st IEEE International Conference on Mining Software Repositories (MSR), 2024
Zhili Zeng, Tao Xiao, Maxime Lamothe, Hideaki Hata, Shane McIntosh [pdf]
DevGPT: Studying Developer-ChatGPT Conversations
Published in 21st IEEE International Conference on Mining Software Repositories (MSR), 2024 (Mining Challenge Proposal)
Tao Xiao, Christoph Treude, Hideaki Hata, Kenichi Matsumoto [pdf]
“My GitHub Sponsors profile is live!” Investigating the Impact of Twitter/X Mentions on GitHub Sponsors
Published in 46th International Conference on Software Engineering (ICSE), 2024
Youmei Fan, Tao Xiao, Hideaki Hata, Christoph Treude, Kenichi Matsumoto [pdf]
Quantifying and Characterizing Clones of Self-Admitted Technical Debt in Build Systems
Published in Empirical Software Engineering (ESE), 2024
Tao Xiao, Zhili Zeng, Dong Wang, Hideaki Hata, Shane McIntosh, Kenichi Matsumoto [pdf]
More than React: Investigating the Role of Emoji Reaction in GitHub Pull Requests
Published in Empirical Software Engineering (ESE), 2023
Dong Wang, Tao Xiao, Teyon Son, Raula Gaikovina Kula, Takashi Ishio, Yasutaka Kamei, Kenichi Matsumoto [pdf]
18 million links in commit messages: purpose, evolution, and decay
Published in Empirical Software Engineering (ESE), 2023
Tao Xiao, Sebastian Baltes, Hideaki Hata, Christoph Treude, Raula Gaikovina Kula, Takashi Ishio, Kenichi Matsumoto [pdf]
Understanding the Role of Images on Stack Overflow
Published in 20th IEEE International Conference on Mining Software Repositories (MSR), 2023
Dong Wang, Tao Xiao, Christoph Treude, Raula Gaikovina Kula, Hideaki Hata, Yasutaka Kamei [pdf]
GitHub Sponsors: Exploring a New Way to Contribute to Open Source
Published in 44th International Conference on Software Engineering (ICSE), 2022
Naomichi Shimada, Tao Xiao, Hideaki Hata, Christoph Treude, Kenichi Matsumoto [pdf]
Characterizing and Mitigating Self-Admitted Technical Debt in Build Systems
Published in IEEE Transactions on Software Engineering (TSE), 2022
Tao Xiao, Dong Wang, Shane McIntosh, Hideaki Hata, Raula Gaikovina Kula, Takashi Ishio, Kenichi Matsumoto [pdf]
More Than React: Investigating The Role of Emoji Reaction in GitHub Pull Requests
Published in 37th International Conference on Software Maintenance and Evolution (ICSME), 2021 (Registered Report)
Teyon Son, Tao Xiao, Dong Wang, Raula Gaikovina Kula, Takashi Ishio, Kenichi Matsumoto [pdf]
Understanding Shared Links and Their Intentions to Meet Information Needs in Modern Code Review: A Case Study of the OpenStack and Qt Projects
Published in Empirical Software Engineering (ESE), 2021
Dong Wang, Tao Xiao, Patanamon Thongtanunam, Raula Gaikovina Kula, Kenichi Matsumoto [pdf]