Arghavan Moradi Dakhel

Amin Nikanjam

Mohammad Hamdaqa

2026-01-29

ArXiv (preprint)

Securing the Model Context Protocol: Defending LLMs Against Tool Poisoning and Adversarial Attacks

Saeid Jamshidi

Kawser Wazed Nafi

Negar Shahabi

Naser Ezzati-Jivan

2025-11-30

arXiv (published)

The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Models

Saeid Jamshidi

Kawser Wazed Nafi

Negar Shahabi

2025-11-30

arXiv (published)

Refactoring with LLMs: Bridging Human Expertise and Machine Understanding

Yonnel Chen Kuang Piao

Jean Carlors Paul

Leuson Da Silva

Mohammad Hamdaqa

2025-10-04

ArXiv (preprint)

Refactoring with LLMs: Bridging Human Expertise and Machine Understanding

Yonnel Chen Kuang Piao

Jean Carlors Paul

Leuson Da Silva

Mohammad Hamdaqa

Code refactoring is a fundamental software engineering practice aimed at improving code quality and maintainability. Despite its importance,… (see more) developers often neglect refactoring due to the significant time, effort, and resources it requires, as well as the lack of immediate functional rewards. Although several automated refactoring tools have been proposed, they remain limited in supporting a broad spectrum of refactoring types. In this study, we explore whether instruction strategies inspired by human best-practice guidelines can enhance the ability of Large Language Models (LLMs) to perform diverse refactoring tasks automatically. Leveraging the instruction-following and code comprehension capabilities of state-of-the-art LLMs (e.g., GPT-mini and DeepSeek-V3), we draw on Martin Fowler's refactoring guidelines to design multiple instruction strategies that encode motivations, procedural steps, and transformation objectives for 61 well-known refactoring types. We evaluate these strategies on benchmark examples and real-world code snippets from GitHub projects. Our results show that instruction designs grounded in Fowler's guidelines enable LLMs to successfully perform all benchmark refactoring types and preserve program semantics in real-world settings, an essential criterion for effective refactoring. Moreover, while descriptive instructions are more interpretable to humans, our results show that rule-based instructions often lead to better performance in specific scenarios. Interestingly, allowing models to focus on the overall goal of refactoring, rather than prescribing a fixed transformation type, can yield even greater improvements in code quality.

2025-10-04

ArXiv (preprint)

Bugs in Large Language Models Generated Code: An Empirical Study

Florian Tambon

Amin Nikanjam

Michel C. Desmarais

Giuliano Antoniol

2025-02-13

Empirical Software Engineering (published)

Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs

Sylvain Kouemo Ngassom

Florian Tambon

2024-07-10

Proceedings of the 1st ACM International Conference on AI-Powered Software (published)

Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs

Sylvain Kouemo Ngassom

Florian Tambon

LLM-based assistants, such as GitHub Copilot and ChatGPT, have the potential to generate code that fulfills a programming task described in … (see more)a natural language description, referred to as a prompt. The widespread accessibility of these assistants enables users with diverse backgrounds to generate code and integrate it into software projects. However, studies show that code generated by LLMs is prone to bugs and may miss various corner cases in task specifications. Presenting such buggy code to users can impact their reliability and trust in LLM-based assistants. Moreover, significant efforts are required by the user to detect and repair any bug present in the code, especially if no test cases are available. In this study, we propose a self-refinement method aimed at improving the reliability of code generated by LLMs by minimizing the number of bugs before execution, without human intervention, and in the absence of test cases. Our approach is based on targeted Verification Questions (VQs) to identify potential bugs within the initial code. These VQs target various nodes within the Abstract Syntax Tree (AST) of the initial code, which have the potential to trigger specific types of bug patterns commonly found in LLM-generated code. Finally, our method attempts to repair these potential bugs by re-prompting the LLM with the targeted VQs and the initial code. Our evaluation, based on programming tasks in the CoderEval dataset, demonstrates that our proposed method outperforms state-of-the-art methods by decreasing the number of targeted errors in the code between 21% to 62% and improving the number of executable code instances to 13%.

2024-05-22

ArXiv (preprint)

Bugs in Large Language Models Generated Code: An Empirical Study

Florian Tambon

Amin Nikanjam

Michel C. Desmarais

Giuliano Antoniol

Large Language Models (LLMs) for code have gained significant attention recently. They can generate code in different programming languages … (see more)based on provided prompts, fulfilling a long-lasting dream in Software Engineering (SE), i.e., automatic code generation. Similar to human-written code, LLM-generated code is prone to bugs, and these bugs have not yet been thoroughly examined by the community. Given the increasing adoption of LLM-based code generation tools (e.g., GitHub Copilot) in SE activities, it is critical to understand the characteristics of bugs contained in code generated by LLMs. This paper examines a sample of 333 bugs collected from code generated using three leading LLMs (i.e., CodeGen, PanGu-Coder, and Codex) and identifies the following 10 distinctive bug patterns: Misinterpretations, Syntax Error, Silly Mistake, Prompt-biased code, Missing Corner Case, Wrong Input Type, Hallucinated Object, Wrong Attribute, Incomplete Generation, and Non-Prompted Consideration. The bug patterns are presented in the form of a taxonomy. The identified bug patterns are validated using an online survey with 34 LLM practitioners and researchers. The surveyed participants generally asserted the significance and prevalence of the bug patterns. Researchers and practitioners can leverage these findings to develop effective quality assurance techniques for LLM-generated code. This study sheds light on the distinctive characteristics of LLM-generated code.

2024-03-13

ArXiv (preprint)

Assessing the Security of GitHub Copilot Generated Code - A Targeted Replication Study

Vahid Majdinasab

Michael Joshua Bishop

Shawn Rasheed

Amjed Tahir