Zejun Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zejun Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Zhi Jin
Peking University
4 shared publications - Ge Li
Shenzhen Graduate School, Peking University, Shenzhen, China
3 shared publications - Fang Liu
School of Design, Hunan University, Changsha, China
1 shared publication - Kaibo Liu
Peking University, Beijing, China
1 shared publication - Kaibo Liu1 shared publication
- Ying Xing
School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China
1 shared publication
Latest Publications
- 1 January 2025
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 40 (1) , 138-157
SAGA: Summarization-Guided Assert Statement Generation
- 1 January 2025
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 40 (1) , 138-157
SAGA: Summarization-Guided Assert Statement Generation
- Top Cited PapersOpen Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1258-1268
HITS: High-coverage LLM-based Unit Test Generation via Method Slicing
Large language models (LLMs) have behaved well in generating unit tests for Java projects. However, the performance for covering the complex focal methods within the projects is poor. Complex methods comprise many conditions and loops, requiring the test cases to be various enough to cover all lines and branches. However, existing test generation methods with LLMs provide the whole method-to-test to the LLM without assistance on input analysis. The LLM has difficulty inferring the test inputs to cover all conditions, resulting in missing lines and branches. To tackle the problem, we propose decomposing the focal methods into slices and asking the LLM to generate test cases slice by slice. Our method simplifies the analysis scope, making it easier for the LLM to cover more lines and branches in each slice. We build a dataset comprising complex focal methods collected from the projects used by existing state-of-the-art approaches. Our experiment results show that our method significantly outperforms current test case generation methods with LLMs and the typical SBST method Evosuite regarding both line and branch coverage scores.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1258-1268
Top Cited PapersOpen AccessHITS: High-coverage LLM-based Unit Test Generation via Method Slicing
Large language models (LLMs) have behaved well in generating unit tests for Java projects. However, the performance for covering the complex focal methods within the projects is poor. Complex methods comprise many conditions and loops, requiring the test cases to be various enough to cover all lines and branches. However, existing test generation methods with LLMs provide the whole method-to-test to the LLM without assistance on input analysis. The LLM has difficulty inferring the test inputs to cover all conditions, resulting in missing lines and branches. To tackle the problem, we propose decomposing the focal methods into slices and asking the LLM to generate test cases slice by slice. Our method simplifies the analysis scope, making it easier for the LLM to cover more lines and branches in each slice. We build a dataset comprising complex focal methods collected from the projects used by existing state-of-the-art approaches. Our experiment results show that our method significantly outperforms current test case generation methods with LLMs and the typical SBST method Evosuite regarding both line and branch coverage scores.
- Open Access
HITS: High-coverage LLM-based Unit Test Generation via Method Slicing
Large language models (LLMs) have behaved well in generating unit tests for Java projects. However, the performance for covering the complex focal methods within the projects is poor. Complex methods comprise many conditions and loops, requiring the test cases to be various enough to cover all lines and branches. However, existing test generation methods with LLMs provide the whole method-to-test to the LLM without assistance on input analysis. The LLM has difficulty inferring the test inputs to cover all conditions, resulting in missing lines and branches. To tackle the problem, we propose decomposing the focal methods into slices and asking the LLM to generate test cases slice by slice. Our method simplifies the analysis scope, making it easier for the LLM to cover more lines and branches in each slice. We build a dataset comprising complex focal methods collected from the projects used by existing state-of-the-art approaches. Our experiment results show that our method significantly outperforms current test case generation methods with LLMs and the typical SBST method Evosuite regarding both line and branch coverage scores.
Open AccessHITS: High-coverage LLM-based Unit Test Generation via Method Slicing
Large language models (LLMs) have behaved well in generating unit tests for Java projects. However, the performance for covering the complex focal methods within the projects is poor. Complex methods comprise many conditions and loops, requiring the test cases to be various enough to cover all lines and branches. However, existing test generation methods with LLMs provide the whole method-to-test to the LLM without assistance on input analysis. The LLM has difficulty inferring the test inputs to cover all conditions, resulting in missing lines and branches. To tackle the problem, we propose decomposing the focal methods into slices and asking the LLM to generate test cases slice by slice. Our method simplifies the analysis scope, making it easier for the LLM to cover more lines and branches in each slice. We build a dataset comprising complex focal methods collected from the projects used by existing state-of-the-art approaches. Our experiment results show that our method significantly outperforms current test case generation methods with LLMs and the typical SBST method Evosuite regarding both line and branch coverage scores.
- 6 March 2023
- Published by Springer Nature in Automated Software Engineering
- Vol. 30 (1) , 1-28
AdaComplete: improve DL-based code completion method’s domain adaptability
- 6 March 2023
- Published by Springer Nature in Automated Software Engineering
- Vol. 30 (1) , 1-28
AdaComplete: improve DL-based code completion method’s domain adaptability