6 papers
Talking to Itself While Coding: What Makes Comments Help Code Generation?
Dangfeng Pan, Zhensu Sun, Cenyuan Zhang +2
Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to generate the code that follows. Howe…
SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
Chenxi Gu, Xiaoning Du, John Grundy
Watermarking has emerged as a promising technique for tracing the authorship of content generated by large language models (LLMs). Among existing approaches, the KGW scheme is part…
Optimizing Knowledge Utilization for Multi-Intent Comment Generation with Large Language Models
Shuochuan Li, Zan Wang, Xiaoning Du +3
Code comment generation aims to produce a generic overview of a code snippet, helping developers understand and maintain code. However, generic summaries alone are insufficient to…
UntrustVul: An Automated Approach for Identifying Untrustworthy Alerts in Vulnerability Detection Models
Lam Nguyen Tung, Xiaoning Du, Neelofar Neelofar +1
Machine learning (ML) has shown promise in vulnerability detection, but ML detectors may rely on irrelevant code features, causing them to highlight non-vulnerable lines as suspici…
Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers
Lam Nguyen Tung, Steven Cho, Xiaoning Du +4
Machine learning (ML) for text classification has been widely used in various domains. These applications can significantly impact ethics, economics, and human behavior, raising se…
Are Latent Vulnerabilities Hidden Gems for Software Vulnerability Prediction? An Empirical Study
Triet H. M. Le, Xiaoning Du, M. Ali Babar
Collecting relevant and high-quality data is integral to the development of effective Software Vulnerability (SV) prediction models. Most of the current SV datasets rely on SV-fixi…