148 citations · 827 across the 63 of their papers we have counts for
14 papers · 1 filter
Less is More? An Empirical Study on Configuration Issues in Python PyPI Ecosystem
Yun Peng, Ruida Hu, Ruoke Wang +3
Python is widely used in the open-source community, largely owing to the extensive support from diverse third-party libraries within the PyPI ecosystem. Nevertheless, the utilizati…
Split and Merge: Aligning Position Biases in LLM-based Evaluators
Zongjie Li, Chaozheng Wang, Pingchuan Ma +4
Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. However, these LLM-based evaluators exhibit po…
REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes
Chaozheng Wang, Zongjie Li, Yun Peng +5
Software plays a crucial role in our daily lives, and therefore the quality and security of software systems have become increasingly important. However, vulnerabilities in softwar…
When Less is Enough: Positive and Unlabeled Learning Model for Vulnerability Detection
Xin-Cheng Wen, Xinchen Wang, Cuiyun Gao +3
Automated code vulnerability detection has gained increasing attention in recent years. The deep learning (DL)-based methods, which implicitly learn vulnerable code patterns, have…
Modeling Software Quality in Virtual Reality Applications from User Feedback
Shuqing Li, Chenran Zhang, Yepang Liu +3
Virtual Reality (VR) applications couple software behavior with head-mounted displays, body movement, spatial interaction, and multimodal feedback. Consequently, familiar software-…
Generative Type Inference for Python
Yun Peng, Chaozheng Wang, Wenxuan Wang +2
Python is a popular dynamic programming language, evidenced by its ranking as the second most commonly used language on GitHub. However, its dynamic type system can lead to potenti…
LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Types
Xin-Cheng Wen, Cuiyun Gao, Feng Luo +3
Prior studies generally focus on software vulnerability detection and have demonstrated the effectiveness of Graph Neural Network (GNN)-based approaches for the task. Considering t…
Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors
Yun Peng, Shuzheng Gao, Cuiyun Gao +2
Although the dynamic type system of Python facilitates the developers in writing Python programs, it also brings type errors at run-time. There exist rule-based approaches for auto…
BadCS: A Backdoor Attack Framework for Code search
Shiyi Qi, Yuanhang Yang, Shuzhzeng Gao +2
With the development of deep learning (DL), DL-based code search models have achieved state-of-the-art performance and have been widely used by developers during software developme…
What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?
Shuzheng Gao, Xin-Cheng Wen, Cuiyun Gao +3
Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models…
On Extracting Specialized Code Abilities from Large Language Models: A Feasibility Study
Zongjie Li, Chaozheng Wang, Pingchuan Ma +5
Recent advances in large language models (LLMs) significantly boost their usage in software engineering. However, training a well-performing LLM demands a substantial workforce for…
Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning
Xin-Cheng Wen, Yupan Chen, Cuiyun Gao +3
Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learnin…
Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models
Shuzheng Gao, Hongyu Zhang, Cuiyun Gao +1
Previous research on code intelligence usually trains a deep learning model on a fixed dataset in an offline manner. However, in real-world scenarios, new code repositories emerge…
Practitioners' Expectations on Code Completion
Chaozheng Wang, Junhao Hu, Cuiyun Gao +5
Code completion has become a common practice for programmers during their daily programming activities. It aims at automatically predicting the next tokens or lines that the progra…