I am an Associate Professor at the Department of Electrical Engineering and Computer Science at York University. I work at the intersection of Software Engineering and Artificial Intelligence. More specifically, my research focuses on 1) taking advantage of AI technologies to address challenging issues of software reliability practices (AI for SE) and 2) developing software reliability assurance techniques to improve the reliability and security of AI infrastructure systems (SE for AI). My research interests include software engineering, software reliability, program analysis, software testing, and machine learning. The tools and techniques developed in my research have already helped detect hundreds of true bugs.

Selected Publications (Full List)

• Retrieval-Augmented Test Generation: How Far Are We?
  Jiho Shin, Nima Shiri Harzevili,Reem Aleithan, Hadi Hemmati, and Song Wang
  ICSE 2026
  PDF

• Evaluating API-Level Deep Learning Fuzzers: A Comprehensive Benchmarking Study
  Nima Shiri Harzevili, Moshi Wei, Mohammad Mahdi Mohajer, Hung Viet Pham, and Song Wang
  ACM Transactions on Software Engineering and Methodology (TOSEM 2025)
  PDF

• Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
  Jiho Shin, Clark Tang, Tahmineh Mohati, Maleknaz Nayebi, Song Wang, Hadi Hemmati
  MSR 2025
  PDF

• Bias Unveiled: Investigating Social Bias in LLM-Generated Code
  Lin Ling, Fazle Rabbi, Song Wang, Jinqiu Yang
  AAAI 2025
  PDF

• ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet?
  Salma Begum Tamanna, Gias Uddin, Song Wang, Lan Xia, Longyu Zhang
  ICSE 2025
  PDF

• One Sentence Can Kill the Bug: Auto-replay Mobile App Crashes from One-sentence Overviews
  Yuchao Huang, Junjie Wang, Zhe Liu, Mingyang Li, Song Wang, Chunyang Chen, Yuanzhe Hu, and Qing Wang
  IEEE Transaction on Software Engineering (TSE 2025)
  PDF

• A Systematic Literature Review on Automated Software Vulnerability Detection Using Machine Learning
  Nima Shiri Harzevili, Alvine Boaye Belle, Junjie Wang, Song Wang, Ming Zhen (Jack) Jiang, and Nachiappan Nagappan
  ACM Computing Surveys 2024 (Impact factor: 23.8)
  PDF

• Assessing Evaluation Metrics for Neural Test Oracle Generation
  Jiho Shin, Hadi Hemmati, Moshi Wei, and Song Wang
  IEEE Transaction on Software Engineering (TSE 2024)
  PDF

• History-Driven Fuzzing For Deep Learning Libraries
  Nima Shiri Harzevili, Mohammad Mahdi Mohajer, Moshi Wei, Hung Viet Pham, and Song Wang
  ACM Transactions on Software Engineering and Methodology (TOSEM 2024)
  PDF

• Deep API Sequence Generation via Golden Solution Samples and API Seeds
  Huang Yuekai, Wang Junjie, Wang Song, Wei Moshi, Shi Lin, Liu Zhe, and Wang Qing.
  ACM Transactions on Software Engineering and Methodology (TOSEM 2024)
  PDF

• Domain Adaptation for Code Model-based Unit Test Case Generation
  Jiho Shin, Sepehr Hashtroudi, Hadi Hemmati, and Song Wang
  ISSTA 2024 (acceptance rate=20% 143/694)
  PDF

• Demystifying and Detecting Misuses of Deep Learning APIs
  Moshi Wei, Nima Shiri Harzevili, Yuekai Huang, Jinqiu Yang, Junjie Wang, and Song Wang
  ICSE 2024 (acceptance rate=22% 234/1053)
  PDF

• Software Testing with Large Language Model: Survey, Landscape, and Vision
  Junjie Wang, Yuchao Huang, Chunyang Chen, Zhe Liu, Song Wang, Qing Wang
  IEEE Transaction on Software Engineering (TSE 2024)
  PDF

• ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification
  Fangwen Mu, Lin Shi, Song Wang, Zhuohao Yu, Binquan Zhang, Chenxue Wang, Shichao Liu, and Qing Wang
  FSE 2024 (acceptance rate=25% 121/483)
  PDF

• The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks
  Jiho Shin, Moshi Wei, Junjie Wang, Lin Shi, and Song Wang
  ACM Transactions on Software Engineering and Methodology (TOSEM 2023)
  PDF

• An Empirical Study on the Stability of Explainable Software Defect Prediction
  Jiho Shin, Reem Aleithan, Jaechang Nam, Junjie Wang, Nima Shiri Harzevili and Song Wang
  APSEC 2023 (acceptance rate=33% 43/128)
  PDF Distinguished Paper Award
  

• Automatic Static Vulnerability Detection for Machine Learning Libraries: Are We There Yet?
  Nima Shiri Harzevili, Jiho Shin, Junjie Wang, Song Wang, and Nachiappan Nagappan
  ISSRE 2023 (acceptance rate=25% 62/247)
  PDF

• Characterizing and Understanding Software Security Vulnerabilities in Machine Learning Libraries
  Nima Shiri Harzevili, Jiho Shin, Junjie Wang, Song Wang, and Nachiappan Nagappan
  MSR 2023 (acceptance rate=37% 43/115)
  PDF

• Developer-Intent Driven Code Comment Generation
  Fangwen Mu, Xiao Chen, Lin Shi, Song Wang, and Qing Wang
  ICSE 2023 (acceptance rate=26% 209/796)
  PDF

• CoCoFuzzing: Testing Neural Code Models with Coverage-Guided Fuzzing
  Moshi Wei, Yuchao Huang, Jinqiu Yang, Junjie Wang, and Song Wang
  IEEE Transactions on Reliability (TR'22)
  PDF

• Automatic Comment Generation via Multi-Pass Deliberation
  Fangwen Mu, Xiao Chen, Lin Shi, Song Wang, and Qing Wang
  ASE 2022 (acceptance rate=22% 116/525)
  PDF

• API Recommendation for Machine Learning Libraries: How Far Are We?
  Moshi Wei, Yuchao Huang, Junjie Wang, Jiho Shin, Shiri harzevili Nima, and Song Wang
  ESEC/FSE 2022 (acceptance rate=22% 99/449)
  PDF

• Are We Building on the Rock? On the Importance of Data Preprocessing for Code Summarization
  Lin Shi, Fangwen Mu, Xiao Chen, Song Wang, Junjie Wang, Ye Yang, Ge Li, Xin Xia, and Qing Wang
  ESEC/FSE 2022 (acceptance rate=22% 99/449)
  PDF

• CLEAR: Contrastive Learning for API Recommendation
  Moshi Wei, Shiri harzevili Nima, Yuchao Huang, Junjie Wang, and Song Wang
  ICSE 2022 (acceptance rate=26% 197/751)
  PDF

• Find Bugs in Static Bug Finders
  Junjie Wang, Yuchao Huang, Song Wang, and Qing Wang
  ICPC 2022 (acceptance rate=41% 41/102)
  ACM SIGSOFT Distinguished Paper Award
  PDF

• Automatic Unit Test Generation for Machine Learning Libraries: How Far Are We?
  Song Wang, Nishtha Shrestha, Abarna Kucheri Subburaman, Junjie Wang, Moshi Wei, and Nachiappan Nagappan
  ICSE 2021 (acceptance rate=22% 138/615)
  PDF

• Context- and Fairness-aware In-process Crowdworker Recommendation
  Junjie Wang, Ye, Yang, Song Wang, Jun Hu, and Qing Wang
  ACM Transactions on Software Engineering and Methodology (TOSEM'21)
  PDF

• Context-aware In-process Crowdworker Recommendation
  Junjie Wang, Ye Yang, Song Wang, Dandan Wang, and Qing Wang.
  ICSE 2020 (acceptance rate=21% 129/617)
  ACM SIGSOFT Distinguished Paper Award
  PDF