8 papers
Learning Generalizable Multimodal Representations for Software Vulnerability Detection
Zeming Dong, Yuejun Guo, Qiang Hu +5
Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture developer intent. However, existin…
When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
Amal AKLI, Mike PAPADAKIS, Maxime CORDY +1
Large language models are increasingly used for code generation, yet the correctness of their outputs depends not only on model capability but also on how tasks are specified. Prio…
Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
Amal Akli, Mike Papadakis, Maxime Cordy +1
Large language models are widely used for code generation, yet they rely on an implicit assumption that the task descriptions are sufficiently detailed and well-formed. However, in…
On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
Mohamed Djilani, Thibault Simonetto, Karim Tit +4
Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, thei…
GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understanding
Zeming Dong, Qiang Hu, Xiaofei Xie +4
Pre-trained code models lead the era of code intelligence, with multiple models designed with impressive performance. However, one important problem, data augmentation for code dat…
When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions
Maya Larbi, Amal Akli, Mike Papadakis +4
Large Language Models (LLMs) have demonstrated impressive performance in code generation tasks under idealized conditions, where task descriptions are clear and precise. However, i…