no description available

Zhipeng Xue

Zhipeng Gao

Shanghai Institute for Advanced Study of Zhejiang University

China

Xing Hu

Zhejiang University

China

Shanping Li

Developers often perform repetitive code editing activities (up to 70%) for various reasons (e.g., code refactoring) during software development. Many deep learning (DL) models have been proposed to automate code editing by learning from the code editing history. Among DL-based models, pre-trained code editing models have achieved the state-of-the-art (SOTA) results. Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task. Existing pre-training tasks mainly are code infilling tasks (e.g., masked language modeling), which are derived from the natural language processing field and are not designed for automatic code editing.

In this paper, we propose a novel pre-training task specialized in code editing and present an effective pre-trained code editing model named CodeEditor. Compared to previous code infilling tasks, our pre-training task further improves the performance and generalization ability of code editing models. Specifically, we collect lots of real-world code snippets as the ground truth and use a powerful generator to rewrite them into mutated versions. Then, we pre-train our CodeEditor to edit mutated versions into the corresponding ground truth, to learn edit patterns. We conduct experiments on four code editing datasets and evaluate the pre-trained CodeEditor in three settings (i.e., fine-tuning, few-shot, and zero-shot). (1) In the fine-tuning setting, we train the pre-trained CodeEditor with four datasets and evaluate it on the test data. CodeEditor outperforms the SOTA baselines by 15%, 25.5%, and 9.4% and 26.6% on four datasets. (2) In the few-shot setting, we train the pre-trained CodeEditor with limited data and evaluate it on the test data. CodeEditor substantially performs better than all baselines, even outperforming baselines that are fine-tuned with all data. (3) In the zero-shot setting, we evaluate the pre-trained CodeEditor on the test data without training. CodeEditor correctly edits 1,113 programs while the SOTA baselines can not work. The results show that the superiority of our pre-training task and the pre-trained CodeEditor is more effective in automatic code editing.

Jia Li

Peking University

China

Ge Li

Peking University

China

Li Zhuo

Zhi Jin

Peking University

China

Xing Hu

Zhejiang University

China

Kechi Zhang

Peking University, China

China

Zhiyi Fu

Peking University

Abstract: Recently, Large Language Models (LLMs) such as GPT-3 and ChatGPT have attracted great attention from both academia and industry. They have shown substantial gains in solving a variety of problems ranging from Q&A to text summarization. Existing studies also found that some LLMs can be applied to the source code, such as code generation or debugging. However, their performance on various software engineering tasks has not been systematically investigated, and the understanding of LLMs is arguably fairly limited. Also, it is unclear how we can build software engineering capability based on LLM. In this talk, I will discuss the performance of LLMs on various software engineering tasks, including code generation, test generation, program repair, code translation, and documentation generation, and present some software engineering applications based on LLM (e.g., . vulnerability management, code search, and code idioms mining).

Xing Hu is an associate professor at school of software technology, Zhejiang University(ZJU). She got my Ph.D degree in July 2020 from School of Electronics Engineering and Computer Science (EECS), Peking University, China. Her research interests are intelligent software engineering (e.g., intelligent code generation and test case generation) and mining software repositories. Her work has been published in major and premier conferences and journals in the area of software engineering and AI.

Xing Hu

Zhejiang University

China

no description available

Zhenhao Li

Concordia University

Canada

An Ran Chen

University of Alberta

Canada

Xing Hu

Zhejiang University

China

Xin Xia

Huawei Technologies

China

Tse-Hsun (Peter) Chen

Concordia University

Canada

Weiyi Shang

University of Waterloo

no description available

Xing Hu

Zhejiang University

China

Zhuang Liu

Zhejiang University

Xin Xia

Huawei Technologies

China

Zhongxin Liu

Zhejiang University

China

Tongtong Xu

Huawei

Xiaohu Yang

Zhejiang University

China

Android applications are getting bigger with an increasing number of features. However, not all the features are needed by a specific user. The unnecessary features can increase the attack surface and cost additional resources (e.g., storage and memory). Therefore, it is important to remove unnecessary features from Android applications. However, it is difficult for the end users to fully explore the apps to identify the unnecessary features, and there is no off-the-shelf tool available to assist users to debloat the apps by themselves. In this work, we propose AutoDebloater to debloat Android applications automatically for end users. AutoDebloater is a web application that can be accessed by end-users through a web browser. In particular, AutoDebloater can automatically explore an app and identify the transitions between activities. Then, AutoDebloater will present the Activity Transition Graph to users and ask them to select the activities they do not want to keep. Finally, AutoDebloater will remove the activities that are selected by users from the app. We conducted a user study on five Android apps downloaded from three categories (i.e., Finance, Tools, and Navigation) in Google Play and F-Droid. The results show that users are satisfied with AutoDebloater in terms of the stability of the debloated apps and the ability of AutoDebloater to identify features that are never noticed before. The tool is available at http://autodebloater.club. The code is available at https://github.com/jiakun-liu/autodebloater/ and the demonstration video can be found at https://youtu.be/Gmz0-p2n9D4

Jiakun Liu

Singapore Management University

Xing Hu

Zhejiang University

China

Ferdian Thung

Singapore Management University

Shahar Maoz

Tel Aviv University

Israel

Eran Toch

Tel Aviv University

Debin Gao

Singapore Management University

David Lo

Singapore Management University

Singapore