About me

Hi, I am Jiho Shin. I am a Ph.D. student in EECS at York University, Toronto.

My research interest is to adopt Deep Learning and NLP techniques for automated software engineering tasks (AI4SE).
Specifically, I investigate the reliability of LLMs in generating software engineering tasks e.g. text-to-source code generation, unit test case generation, test oracle (assertions) generation, automatic program repair (APR), code comments, code translation, etc.

Currently, I am looking for research positions in North America (US and Canada) to achieve better reliability of LLMs in code intelligence tasks.

Publication

Conference Papers

8. Domain Adaptation for Deep Unit Test Case Generation
Jiho Shin, Sepehr Hashtroudi, Hadi Hemmati, Song Wang
2023 arXiv preprint, (Under Review at a top testing conference, Major Revision)
7. Prompt Engineering or Fine-Tuning: An Empirical Assessment of Large Language Models in Automated Software Engineering Tasks
Jiho Shin, Clark Tang, Tahmineh Mohati, Maleknaz Nayebi, Song Wang, Hadi Hemmati
2023 arXiv preprint, (Under Review at TSE)
6. Assessing Evaluation Metrics for Neural Test Oracle Generation
Jiho Shin, Hadi Hemmati, Moshi Wei, Song Wang
2023 arXiv preprint, (Under Review at TSE, Major Revision)
5. An Empirical Study on the Stability of Explainable Software Defect Prediction
Jiho Shin, Reem Aleithan, Jaechang Nam, Junjie Wang, Nima Shiri Harzevili, Song Wang
2023 30th Asia-Pacific Software Engineering Conference (APSEC)
🏆 Distinguished Paper Award
4. Automatic Static Vulnerability Detection for Machine Learning Libraries: Are We There Yet?
Nima Shiri Harzevili, Jiho Shin, Junjie Wang, Song Wang, Nachiappan Nagappan
2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE)
3. Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries
Nima Shiri Harzevili, Jiho Shin, Junjie Wang, Song Wang, Nachiappan Nagappan
2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)
2. API Recommendation for Machine Learning Libraries: How Far Are We?
Moshi Wei, Yuchao Huang, Junjie Wang, Jiho Shin, Nima Shiri Harzevili, Song Wang
2022 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)
1. Similar Patch Recommendation for Actionable Defect Prediction
Jiho Shin and Jaechang Nam
2020 Proceedings of the 22nd Korea Conference on Software Engineering (KCSE)
🏆 Distinguished Paper Award

Journal Papers

2. The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks
Jiho Shin, Moshi Wei, Junjie Wang, Lin Shi, Song Wang
2023 ACM Transactions on Software Engineering and Methodology (TOSEM)
1. A Survey of Automatic Code Generation from Natural Language
Jiho Shin and Jaechang Nam
2021 Journal of Information Processing Systems (JIPS)

Education

York University, Toronto 2021 ~ Present

Dept. of EECS Ph.D.

Research Field: AI/ML for Software Engineering, Code Generation, Automated Software Testing, LLM for SE

Supervisors: Dr. Song Wang and Dr. Hadi Hemmati

Handong Global University, Pohang 2019 ~ 2021

Dept. of CSEE M.Sc.

Research Field: Code Generation, Actionable and Explainable Defect Prediction

Supervisor: Dr. Jaechang Nam

Thesis: Actionable Defect Prediction

Handong Global University, Pohang 2012 ~ 2019

Dept. of CSEE B.Sc.

Specialization: Web Application, Human-Computer Interaction, Computer Vision

experience

York University

Graduate Research Assistant Sep. 2021 ~ Present

Teaching Assistant Sep. 2021 ~ Present

Handong Global University

Graduate Research Assistant Mar. 2019 ~ Feb. 2021

Teaching Assistant Sep. 2018 ~ Dec. 2020

Republic of Korea Navy