* My name, i.e., Thanh Le-Cong is bolded in publications belows
+ denotes equal contributions
Working Papers
[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:
[Arxiv] GNNInfer: Property Inference for Graph Neural Network
Authors: Dat Nguyen , Hieu M. Vu , Thanh Le-Cong, Bach Le, David Lo, Corina Pasareanu
Venue: Under Review in IEEE Transaction on Software Engineering
One-line Abstract: The first automatic property inference technique for GNNs using formal verification, graph mining and dynamic analysis
Links:
[Arxiv] Adversarial Patch Generation for Automatic Program Repair
Authors: Abdulaziz Alhefdhi, Hoa Khanh Dam, Thanh Le-Cong, Xuan-Bach D Le, Aditya Ghose
Venue: Under Review in Springer Software Quality Journal
One-line Abstract: A new training paradigm for Neural Program Repair using Generative Adversarial Network
Links:
Selected Publications
For a full list of publications, please refer to my Google Scholar profile.
[TSE'24] Leveraging Large Language Model for Automatic Patch Correctness Assessment
Authors: Xin Zhou, Bowen Xu, Kisub Kim, DongGyun Han, Hung Nguyen, Thanh Le-Cong, Junda He, Bach Le, and David Lo
Venue: IEEE Transactions on Software Engineering
One-line Abstract: Zero-shot Patch Correctness Assessment with Large Language Models
Links:
[EASE'24] LEGION: Harnessing Pre-trained Language Models for GitHub Topic Recommendations with Distribution-Balance Loss
Authors: Yen-Trang Dang, Thanh Le-Cong, Phuc-Thanh Nguyen, Anh T. M. Bui, Phuong T. Nguyen, Bach Le, Quyet-Thang Huynh
Venue: 28th International Conference on Evaluation and Assessment in Software Engineering (EASE), Research Track [Acceptance Rate: 25%]
One-line Abstract: Address Long-tailed Distribution on GitHub Topic Recommendation using Distribution-Balance Loss and Pre-trained Language Models
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:
[ASE'23] Are We Ready to Embrace Generative AI for Software Q&A?
Authors: Bowen Xu, Thanh-Dat Nguyen, Thanh Le-Cong, Thong Hoang, Jiakun Liu, Kisub Kim, Chen Gong, Changan Niu, Chenyu Wang, Bach Le, David Lo
Venue: IEEE/ACM 35th International Conference on Automated Software Engineering (ASE) 2023, New Ideas and Emerging Results (NIER) Track [Acceptance Rate: 36%]
One-line Abstract: A comparative evaluation between ChatGPT-generated and Human answers for Software Q&A.
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:
[TSE'23] 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:
[SANER'23] Topic Recommendation for GitHub Repositories: How Far Can Extreme Multi-Label Learning Go
Authors: Ratnadira Widyasari, Zhao Zhipeng, Thanh Le-Cong, Hong Jin Kang, and David Lo
Venue: IEEE 30th International Conference on Software Analysis, Evolution and Reengineering (SANER) 2023, Research Track [Acceptance Rate: 27%]
One-line Abstract: An exploration study about the effectiveness of XML techniques on Github Topic Recommendation.
Links:
[ICSE'23] Chronos: Time-Aware Zero-Shot Identification of Libraries from Vulnerability Reports
Authors: Yunbo Lyu+, Thanh Le-Cong+, Hong Jin Kang, Ratnadira Widyasari, Zhao Zhipeng, Bach Le, Ming Li, and David Lo
Venue: IEEE/ACM 45th International Conference on Software Engineering (ICSE) 2023, Technical Track [Acceptance Rate: 26%]
One-line Abstract: Identifying vulnerable libraries from vulnerability reports via zero-shot learning and domain-specific mechanisms.
Links:
[ICSME'23] FFL: Fine-grained Fault Localization for Student Programs via Syntactic and Semantic Reasoning
Authors: Thanh-Dat Nguyen, Thanh Le-Cong, Duc-Minh Luong, Van-Hai Duong, Bach Le, David Lo, and Quyet-Thang Huynh
Venue: IEEE 38th International Conference on Software Maintenance and Evolution (ICSME) 2022, Research Track [Acceptance Rate: 23%]
One-line Abstract: Automatically identifying fault locations in student programs by applying Graph Neural Network on a fine-grained graph-based representation of the program, which combines AST with test coverage information.
Authors:Thanh Le-Cong, Hong Jin Kang, Truong Giang Nguyen, Stefanus Agus Haryono, David Lo, Bach Le, and Thang Huynh Quyet
Venue: ACM 30th Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2022, Research Track [Acceptance Rate: 22%]
One-line Abstract: Pruning false positives in static call graph via code features learned by Large Language Model and syntactic features extracted from the original call graph.
Links:
[FSE'22] VulCurator: A Vulnerability-Fixing Commit Detector
Authors: Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang, Bach Le, and David Lo
Venue: ACM 30th Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2022, Tool Demos Track [Acceptance Rate: 56%]
One-line Abstract: Identifying vulnerability-fixing commits by applying Large Language Model on multiple sources including code changes, commit messages, and related issues.
Links:
[ICSE'22] Toward the Analysis of Graph Neural Networks
Authors: Thanh-Dat Nguyen+, Thanh Le-Cong+, ThanhVu H. Nguyen, Bach Le, and Quyet-Thang Huynh
Venue: IEEE/ACM 44th International Conference on Software Engineering (ICSE) 2022, New Ideas and Emerging Results (NIER) Track [Acceptance Rate: 22%]
One-line Abstract: Discovering formal properties of GNNs by converting them into FFNNs and reusing existing FFNNs analyses.
Links:
[ISSRE'21] Usability and Aesthetics: Better Together for Automated Repair of Web Pages
Authors:Thanh Le-Cong, Bach Le, Quyet-Thang Huynh, and Phi Le Nguyen
Venue: IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE) 2021, Research Track [Acceptance Rate: 27%]
One-line Abstract: Automatically repairing mobile-unfriendly web pages using Evolutionary Optimization.
