12 papers
From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
Anh Ho, Thanh Le-Cong, Bach Le +1
[...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed to fix general software bugs. Unfortuna…
FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code Generation
Loc Pham, Lang Hong Nguyet Anh, Thanh Le-Cong
Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Hask…
Mapping NVD Records to Their Vulnerability-fixing Commits: How Hard is It?
Huu Hung Nguyen, Ting Zhang, Duc Manh Tran +7
Mapping National Vulnerability Database (NVD) records to vulnerability-fixing commits (VFCs) is crucial for vulnerability analysis but challenging due to sparse explicit links in N…
PatchGuru: Patch Oracle Inference from Natural Language Artifacts
Thanh Le-Cong, Bach Le, Toby Murray +2
As software systems evolve, patches may unintentionally alter program behavior. Validating patches against their intended semantics is difficult due to incomplete regression tests…
How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
Hua Yang, Alejandro Velasco, Thanh Le-Cong +3
The success of large language models for code relies on vast amounts of code data, including public open-source repositories, such as GitHub, and private, confidential code from co…
Perish or Flourish? A Holistic Evaluation of Large Language Models for Code Generation in Functional Programming
Nguyet-Anh H. Lang, Eric Lang, Thanh Le-Cong +2
Functional programming provides strong foundations for developing reliable and secure software systems, yet its adoption remains not widespread due to the steep learning curve. Rec…