[ACL’25] Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference.
Cong-Thanh Le, Bach Le, Toby Murray
CV
Education
- Ph.D in Version Control Theory, GitHub University, 2018 (expected)
- M.S. in Jekyll, GitHub University, 2014
- B.S. in GitHub, GitHub University, 2012
Work experience
- Spring 2024: Academic Pages Collaborator
- GitHub University
- Duties includes: Updates and improvements to template
- Supervisor: The Users
- Fall 2015: Research Assistant
- GitHub University
- Duties included: Merging pull requests
- Supervisor: Professor Hub
- Summer 2015: Research Assistant
- GitHub University
- Duties included: Tagging issues
- Supervisor: Professor Git
Skills
- Skill 1
- Skill 2
- Sub-skill 2.1
- Sub-skill 2.2
- Sub-skill 2.3
- Skill 3
Publications
[CoqPL’25] Towards Mining Robust Coq Proof Patterns (Extended Abstract/Vision)
Cezary Kaliszyk, Bach Le, Christine Rizkallah
[TOSEM’25] When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair.
Wenqiang Luo, Jacky Wai Keung, Bo Yang, He Ye, Claire Le Goues, Tegawende F Bissyande, Haoye Tian, Bach Le
[TOSEM’25] Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing.
Cong-Thanh Le, Thanh-Dat Nguyen, Bach Le, Toby Murray
[SQJ’25] Adversarial Patch Generation for Automated Program Repair.
Aziz Alhefdhi, Khanh-Hoa Dam, Cong-Thanh Le, Bach Le, Aditya Ghose
[JSS’25] EnseSmells: Deep ensemble and programming language models for automated code smells detection
Anh Ho, Phuong T. Nguyen, Mai Anh T. Bui, Amleto Di Salle, Bach Le
[ISSTA’24] VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction.
Thanh-Dat Nguyen, Tung Do-Viet, Hung Nguyen-Duy, Tuan-Hai Luu, Hung Le, Bach Le, Patanamon (Pick) Thongtanunam
[EASE’24] LEGION: Harnessing Pre-trained Language Models for GitHub Topic Recommendations with Distribution-Balance Loss.
Yen-Trang Dang, Cong-Thanh Le, Phuc-Thanh Nguyen, Mai-Anh Bui, Phuong T. Nguyen, Bach Le, Quyet-Thang Huynh
[ICST’24] Does Going Beyond Branch Coverage Make Program Repair Tools More Reliable?
Amirfarhad Nilizadeh, Gary T. Leavens, Corina Pasareanu, Xuan-Bach D. Le, David Cok
[TOSEM’24] Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues.
Yue Liu, Cong-Thanh Le, Ratnadira Widyasari, Chakkrit Tantithamthavorn, Li Li, Xuan Bach D. Le, David Lo
[TSE’24] Leveraging Large Language Model for Automatic Patch Correctness Assessment.
Xin Zhou, Bowen Xu, Kisub Kim, DongGyun Han, Hung Nguyen, Thanh Le-Cong, Junda He, Bach Le, and David Lo
[ASE’23] Are We Ready to Embrace Generative AI for Software Q&A?
Bowen Xu, Thanh-Dat Nguyen, Thanh Le-Cong, Thong Hoang, Jiakun Liu, Kisub Kim, Chen GONG, Changan Niu, Chenyu Wang, Xuan-Bach D. Le, David Lo
[TSE’23] Multi-Granularity Detector for Vulnerability Fixes.
Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang, Ratnadira Widyasari, Chengran Yang, Zhipeng Zhao, Bowen Xu, Jiayuan Zhou, Xin Xia, Ahmed Hassan, Xuan-Bach D. Le, David Lo
[TSE’23] Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning.
Thanh Le-Cong, Duc-Minh Luong, Xuan-Bach D. Le, David Lo, Nhat-Hoa Tran, Quang-Huy Bui, Quyet-Thang Huynh
[FoSSaCS’23] An Efficient Cyclic Entailment Procedure in a Fragment of Separation Logic.
Quang-Loc Le, Xuan-Bach D. Le
[ICSME’23] The Future Can’t Help Fix The Past: Assessing Program Repair In The Wild (Distinguished Paper Award)
Vinay Kabadi, Dezhen Kong, Siyu Xie, G. Arthar, Lingfeng Bao, Tien-Duy BL, Xuan-Bach D. Le, and David Lo
[ICSE’23] Chronos: Time-Aware Zero-Shot Identification of Libraries from Vulnerability Reports.
Y. Lyu, Thanh Le-Cong, Hong Jin Kang, R. Widyasari, Z. Zhao, Xuan-Bach D. Le, Ming Li, David Lo
[Software Verification, Book Chapter] Recent Advances in Symbolic Pathfinder.
Corina Pasareanu, Yannic Noller, Aymeric Fromherz, Bach D.X. Le, Wilem Visser, Tevfik Bultan, and William Eiers
[ESEC/FSE’22] AutoPruner: Transformer-based Call Graph Pruning.
Thanh Le-Cong, Hong Jin Kang, Truong Giang Nguyen, S. Haryono, David Lo, Xuan-Bach D. Le, and Quyet-Thang Huynh
[ESEC/FSE’22] VulCurator: A Vulnerability-Fixing Commit Detector.
Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang, Xuan-Bach D. Le, David Lo
[ICSME’22] FFL: Fine grained Fault Localization for Student Programs via Syntactic and Semantic Reasoning.
Thanh-Dat Nguyen, Thanh Le-Cong, Duc-Minh Luong, Van-Hai Duong, Xuan-Bach D. Le, David Lo and Quyet-Thang Huynh
[ISSTA’22] Test Mimicry to Assess the Exploitability of Library.
Hong Jin Kang, Truong Giang Nguyen, Xuan-Bach D. Le, David Lo, Corina Pasareanu
[ICSE’22] Toward the Analysis of Graph Neural Networks.
Thanh-Dat Nguyen, Thanh Le-Cong, ThanhVu H Nguyen, Xuan-Bach D. Le, Quyet-Thang Huynh
[ISSRE’21] REFIXAR: Multi-version Reasoning for Automated Repair of Regression Errors.
Xuan-Bach D. Le, Quang-Loc Le
[ISSRE’21] More Reliable Test Suites for Dynamic Program Repair by Using Counterexamples.
Amirfarhad Nilizadeh, Marlon Calvo, Gary T. Leavens, and Xuan-Bach D. Le
[ISSRE’21] Usability and Aesthetics: Better Together for Automated Repair of Web Pages.
Cong-Thanh Le, Xuan-Bach D. Le, Quyet-Thang Huynh, Phi Le Nguyen
[ICST’21] Exploring True Test Overfitting in Dynamic Automated Program Repair using Formal Methods
Amirfarhad Nilizadeh, Gary T. Leavens, Xuan-Bach D. Le, Corina Pasareanu, and David R. Cok
[JPF’19] SAFFRON: Adaptive Grammar-based Fuzzing for Worst-Case Analysis
Xuan-Bach D. Le, Corina Pasareanu, Rohan Padhye, David Lo, Willem Visser, and Koushik Sen
[ICSE’19] On Reliability of Patch Correctness Assessment
Xuan-Bach D. Le, Lingfeng Bao, David Lo, Xia Xin, Shanping Li, and Corina Pasareanu
[SV-COMP’19] Symbolic Pathfinder for SV-COMP
Yannic Noller, Corina Pasareanu, Aymeric Fromherz, Xuan-Bach D. Le, and Willem Visser
[TSE’19] Smart Contract Development: Challenges and Opportunities
Z. Weiqin, L. David, S. K. Pavneet, Xuan-Bach D. Le, F. Yang, Zhenyu Chen, and Baowen Xu
[EmSE-ICSE’18] Overfitting in Semantics-Based Automated Program Repair
Xuan-Bach D. Le, Ferdian Thung, David Lo, Claire Le Goues
[ESEC/FSE’17] XSearch: A Domain-Specific Cross-Language Relevant Question Retrieval Tool
Bowen Xu, Zhenchang Xing, Xin Xia, David Lo and Xuan-Bach D. Le
[ESEC/FSE’17] S3: Syntax- and Semantic-Guided Repair Synthesis via Programming by Examples
Xuan Bach D. Le, Duc Hiep Chu, David Lo, Claire Le Goues, and Willem Visser.
[ISSTA’17] JFIX: Semantics-Based Repair of Java Programs via Symbolic PathFinder
Xuan Bach D. Le, Duc Hiep Chu, David Lo, Claire Le Goues, and Willem Visser.
[ICSME’16] Empirical Study on Synthesis Engines for Semantics-based Program Repair
Xuan Bach D. Le, David Lo, Claire Le Goues
[ICSME’16] Enhancing Automated Program Repair with Deductive Verification
Xuan Bach D. Le, Quang Loc Le, David Lo, Claire Le Goues
[ICSME’16] Recommending Code Changes for Automatic Backporting of Linux Device Drivers
Ferdian Thung, Xuan-Bach D. Le, David Lo, Julia L. Lawall
[SANER’16] History Driven Program Repair
Xuan-Bach D. Le, David Lo, Claire Le Goues
[ISSRE’15] Should Fixing These Failures be Delegated to Automated Program Repair?
Xuan-Bach D. Le, Tien-Duy B. Le, David Lo
[ASE’15] Synergizing Specification Miners through Model Fissions and Fusions
Tien-Duy B. Le, Xuan-Bach D. Le, David Lo, and Ivan Beschastnikh
[ICPC’15] Active Semi-supervised Defect Categorization
Ferdian Thung, Xuan-Bach D. Le, David Lo
Talks
Conference Proceeding talk 3 on Relevant Topic in Your Field
Conference proceedings talk at Testing Institute of America 2014 Annual Conference, Los Angeles, CA, USA
Talk 2 on Relevant Topic in Your Field
Talk at London School of Testing, London, UK
Tutorial 1 on Relevant Topic in Your Field
Tutorial at UC-Berkeley Institute for Testing Science, Berkeley, CA, USA
Talk 1 on Relevant Topic in Your Field
Talk at UC San Francisco, Department of Testing, San Francisco, CA, USA
Teaching
Service and leadership
- Currently signed in to 43 different slack teams