Thanh Le-Cong

PhD Student/Graduate Researcher at The University of Melbourne

Contact:

Address: Desk 2.075, Level 2, Melbourne Connect, 700 Swanston St, Carlton, Melbourne, Victoria, Australia
Email: congthanh.le student.unimelb.edu.au
Social Networks:
Research Profiles: [ Google Scholar] [ DBLP] [ ORCID] [ Scorpus]

About Me

I am Thanh Le-Cong (Lê Công Thành in Vietnamese), a second-year Ph.D. student at CIS, The University of Melbourne . During my PhD, I am fortunate to be advised by Dr. Bach Le and Prof. Toby Murray, and supported by Melbourne Research Scholarship and Google PhD Fellowship. Before joining UoM, I worked as a research engineer at SOAR (SOftware Analytic Research), Singapore Management University under the advisor of Prof. David Lo. I was also an applied scientist intern of Automated Reason Group at Amazon Web Services.

My passion lies in leveraging AI and data mining to tackle real-world challenges in software engineering and pushing the boundaries of programming technologies. My goal to is to build trustworthy AI-powered tools for supporting developers on software engineering tasks (AI4SE), especially bug fixing and management. Particular, I’m trying to explore the following research questions:

(1) How reliable and depandable AI4SE tools?

(2) How can we improve their reliability and trustworthiness?

(3) How can we improve developers’ trust on these tools?

If they are look interesting for you, let's see more about my publications.

Research interests:

News

[August 2024] Our paper entitled Leveraging Large Language Model for Automatic Patch Correctness Assessment is accepted by IEEE Transactions on Software Engineering(TSE).
[March 2024] Our paper entitled LEGION: Harnessing Pre-trained Language Models for GitHub Topic Recommendations with Distribution-Balance Loss is accepted by International Conference on Evaluation and Assessment in Software Engineering (EASE).
[Feb 2024] I will join Amazon this summer as an Applied Scientist Intern in Automated Reasoning.
[Jan 2024] Our paper entitled Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues? is accepted by ACM Transactions on Software Engineering and Methodology.
[Dec 2023] Our TSE paper Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning is accepted for presentation as a part of Journal-First Track at ICSE 2024. See you in Lisbon!
[Oct 2023] I have been awarded Google PhD Fellowships in Programming Technology and Software Engineering. Huge thanks to my advisors, colleagues, and collaborators!
[Jul 2023] Our paper entitled "Are We Ready to Embrace Generative AI for Software Q&A?" is accepted by ASE 2023.
[May 2023] Our paper entitled "Multi-granularity Detector for Vulnerability Fixes" is accepted by IEEE Transactions on Software Engineering.

Educations

The University of Melbourne, Ph.D. in Engineering and IT, supervised by Dr. Bach Le and Prof. Toby Murray, Feb 2023 - Aug 2026 (expected).
Hanoi University of Science and Technology, B.S. in Information Technology (Talented Engineering Program), Sep 2016 - Jun 2021.

Recent Publications

[Arxiv] Semantic-guided Search for Efficient Program Repair with Large Language Models

Authors: Thanh Le-Cong, Bach Le, Toby Murray
One-line Abstract: A memory efficient LLM-based Prorgam Repair technique with Monte Carlo Tree Search
Links:

[Arxiv] Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing

Authors: Thanh Le-Cong, Dat Nguyen, Bach Le, Toby Murray
Venue: Under Review in ACM Transactions on Software Engineering and Methodology
One-line Abstract: An empirical study on the naturalness of semantic-preserving transformations and their impact on evaluating Neural Program Repair
Links:

[TOSEM'24] Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues?

Authors: Yue Liu, Thanh Le-Cong, Ratnadira Widyasari, Chakkrit Tantithamthavorn, Li Li, Bach Le, David Lo
Venue: ACM Transactions on Software Engineering and Methodology
One-line Abstract: An empirical study on code quality issues in ChatGPT-generated code.
Links:

[TSE'23-ICSE'24] Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning

Authors: Thanh Le-Cong, Duc-Minh Luong, Bach Le, David Lo, Nhat Hoa Tran, Quang Huy Bui and Quyet Thang Huynh
Venue: IEEE Transactions on Software Engineering
One-line Abstract: Reasoning about the correctness of APR-generated patches via program invariants and code representation learning.
Accepted for presentation at IEEE/ACM 46th International Conference on Software Engineering 2024 as a part of Journal-First Track
Links:

[TSE'23] MiDas: Multi-Granularity Detector for Vulnerability Fixes

Authors: Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang, Ratnadira Widyasari, Chengran Yang, Zhipeng Zhao, Bowen Xu, Jiayuan Zhou, Xin Xia, Ahmed E. Hassan, Bach Le, and David Lo
Venue: IEEE Transactions on Software Engineering
One-line Abstract: Identifying vulnerability fixes by analyzing multi-granularity of code changes.
Integrated to internal service of industry partners for managing vulnerability
Links: