检索结果-内蒙古大学图书馆

DALO-APR: LLM-based automatic program repair with data augmentation and loss function optimization

JOURNAL OF SUPERCOMPUTING 2025年第5期81卷

作者： Wang, Shaosheng Lu, Lu Qiu, Shaojian Tian, Qingyan Lin, Haishan South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China Guangdong Artificial Intelligence & Digital Econ L Guangzhou 510320 Guangdong Peoples R China Pengcheng Lab Shenzhen 518055 Guangdong Peoples R China South China Agr Univ Coll Math & Informat Guangzhou 510642 Guangdong Peoples R China Guangdong Prov Key Lab Tunnel Engn Safety & Emerge Guangzhou 510440 Guangdong Peoples R China

automatic program repair (APR) has made significant strides with the advent of large language models (LLMs) such as T5 and CodeT5. However, LLM-based APR models may rely on repetitive repair patterns due to limited training data diversity, resulting in suboptimal performance. Additionally, common loss functions, such as cross-entropy, may not fully prioritize repair locations or optimize the model's output probability distribution to favor more accurate repair candidates. To address these challenges, this paper proposes a method for LLM-Based APR with Data Augmentation and Loss Function Optimization (DALO-APR). The data augmentation strategy expands the variety of repair patterns by randomly deleting, inserting, swapping tokens, and injecting errors. The optimized loss function helps the model rank more accurate repair candidates higher. Experimental results on Java, JavaScript, Python, and C datasets demonstrate that DALO-APR improves both error localization and bug fixing. Compared to baseline models, DALO-APR shows improvements across multiple metrics, especially with a 105.65% increase in 100% accuracy.

关键词： automatic program repair Large language models Data augmentation Loss function

来源：评论

学校读者我要写书评

暂无评论

automatic program repair via Learning Edits on Sequence Code Property Graph 29

Automatic Program Repair via Learning Edits on Sequence Code...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Li, Xiaoyu Wu, Jingzheng Ling, Xiang Luo, Tianyue Wu, Yanjun Institute of Software Chinese Academy of Sciences Intelligent Software Research Center China University of Chinese Academy of Sciences China

ISBN: (纸本)9798350330717

In recent years, deep learning has been widely applied in the research of automatic program repair, namely, learning-based program repair, which treats the program repair task as either a neural machine translation problem or a transformation toward the abstract syntax tree of the program. However, all existing learning-based program repair solutions have not adequately modeled the deep semantic information of the programs. To be specific, those solutions based on neural machine translation do not involve any semantic information of the programs at all, while other solutions based on abstract syntax tree transformations also do not involve information such as control flow and data flow. Additionally, the neural networks they use are also unable to sufficiently learn the semantic information. As a result, they cannot fix some bugs that involve semantic *** this paper, we propose a new learning-based program repair approach called SGEPR. SGEPR uses a novel intermediate representation named sequence code property graph (SCPG) to model program semantic information, which can cover multiple types of semantic information in the program. SGEPR then utilizes a graph neural network based on the attention mechanism to learn the semantic information within SCPG. Finally, a well-designed prediction network is employed to generate the repair patches for the buggy program. To evaluate the performance of SGEPR, we conducted comparative experiments on a real-world dataset and the results show that SGEPR can achieve a top-3 accuracy of 56.85%, which is 15.69% higher than the state-of-the-art learning-based program repair method. © 2023 IEEE.

关键词： automatic program repair graph neural network program representation

来源：评论

学校读者我要写书评

暂无评论

Improving Search-Based automatic program repair With Neural Machine Translation

引用

IEEE ACCESS 2022年 10卷 51167-51175页

作者： Li, Dongcheng Wong, W. Eric Jian, Mingyong Geng, Yi Chau, Matthew Univ Texas Dallas Dept Comp Sci Richardson TX 75080 USA China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China

The challenge of automatically repairing bugs in programs to reduce debugging expenses and increase program quality is known as automated program repair. To overcome this issue, test-suite-based repair techniques use a specified test suite as an oracle and alter the input faulty program to pass the full test suite. GenProg is a well-known example of this kind of repair, in which genetic programming is used to reorder the statements already present in the faulty program. However, recent practical experiments suggest that GenProg's performance, notably for Java, is not sufficient. Improved program dependability necessitates the use of automatic program repair techniques. Template-based program repair techniques have recently been combined with search-based techniques to solve program issues automatically. Although intriguing, it has two fundamental drawbacks: Its search space often lacks the correct solution, and the technique disregards program expertise, such as precise code language. Compared with the template-based program repair approach, existing neural-machine-translation-based approaches are not limited by these constraints due to their ability to learn and generate new solutions. We propose an approach that combines a search-based automatic program repair technique with a neural-machine-translation-based approach. More specifically, we use both redundancy assumption and sequence-to-sequence learning of correct patches as the source for potential fix statements that feed into a multiobjective evolutionary search algorithm to find test-suite-adequate patches. In this work, a novel framework called ARJANMT is introduced for automatically repairing Java programs. Two sets of controlled experiments are conducted on 410 bugs from two benchmarks to investigate the repairability and correctness of our proposed framework. A comparison between state-of-the-art automatic program repair frameworks is made. The experimental results indicate that combining those two types

关键词： Maintenance engineering Codes Computer bugs Java Genetic programming Termination of employment Task analysis Search-based software engineering automatic program repair multi-objective optimization genetic programming neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Evaluating automatic program repair Capabilities to repair API Misuses

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2021年第7期48卷 2658-2679页

作者： Kechagia, Maria Mechtaev, Sergey Sarro, Federica Harman, Mark UCL Dept Comp Sci London WC1E 6BT England Facebook London London W1T 1FB England

API misuses are well-known causes of software crashes and security vulnerabilities. However, their detection and repair is challenging given that the correct usages of (third-party) apis might be obscure to the developers of client programs. This paper presents the first empirical study to assess the ability of existing automated bug repair tools to repair api misuses, which is a class of bugs previously unexplored. Our study examines and compares 14 Java test-suite-based repair tools (11 proposed before 2018, and three afterwards) on a manually curated benchmark (APIRepBench) consisting of 101 api misuses. We develop an extensible execution framework (APIARTy) to automatically execute multiple repair tools. Our results show that the repair tools are able to generate patches for 28 percent of the api misuses considered. While the 11 less recent tools are generally fast (the median execution time of the repair attempts is 3.87 minutes and the mean execution time is 30.79 minutes), the three most recent are less efficient (i.e., 98 percent slower) than their predecessors. The tools generate patches for api misuses that mostly belong to the categories of missing null check, missing value, missing exception, and missing call. Most of the patches generated by all tools are plausible (65 percent), but only few of these patches are semantically correct to human patches (25 percent). Our findings suggest that the design of future repair tools should support the localisation of complex bugs, including different categories of api misuses, handling of timeout issues, and ability to configure large software projects. Both APIRepBench and APIARTy have been made publicly available for other researchers to evaluate the capabilities of repair tools on detecting and fixing api misuses.

关键词： Tools Maintenance engineering Computer bugs Benchmark testing Software Java Security automatic program repair Application programming Interfaces (APIs) API misuses bug benchmarks

来源：评论

学校读者我要写书评

暂无评论

Let's Talk With Developers, Not About Developers: A Review of automatic program repair Research

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2023年第1期49卷 419-436页

作者： Winter, Emily Nowack, Vesna Bowes, David Counsell, Steve Hall, Tracy Haraldsson, Saemundur Woodward, John Univ Lancaster Sch Comp & Commun Lancaster LA1 4YW England Brunel Univ London Dept Comp Sci London UB8 3PH England Univ Stirling Dept Comp Sci & Math Stirling FK9 4LA England Queen Mary Univ London Sch Elect Engn & Comp Sci London E1 4NS England

automatic program repair (APR) offers significant potential for automating some coding tasks. Using APR could reduce the high costs historically associated with fixing code faults and deliver significant benefits to software engineering. Adopting APR could also have profound implications for software developers ' daily activities, transforming their work practices. To realise the benefits of APR it is vital that we consider how developers feel about APR and the impact APR may have on developers ' work. Developing APR tools without consideration of the developer is likely to undermine the success of APR deployment. In this paper, we critically review how developers are considered in APR research by analysing how human factors are treated in 260 studies from Monperrus 's Living Review of APR. Over half of the 260 studies in our review were motivated by a problem faced by developers (e.g., the difficulty associated with fixing faults). Despite these human-oriented motivations, fewer than 7% of the 260 studies included a human study. We looked in detail at these human studies and found their quality mixed (for example, one human study was based on input from only one developer). Our results suggest that software developers are often talked about in APR studies, but are rarely talked with. A more comprehensive and reliable understanding of developer human factors in relation to APR is needed. Without this understanding, it will be difficult to develop APR tools and techniques which integrate effectively into developers ' workflows. We recommend a future research agenda to advance the study of human factors in APR.

关键词： Human factors software development automatic program repair

来源：评论

学校读者我要写书评

暂无评论

The effectiveness of context-based change application on automatic program repair

引用

EMPIRICAL SOFTWARE ENGINEERING 2020年第1期25卷 719-754页

作者： Kim, Jindae Kim, Jeongho Lee, Eunseok Kim, Sunghun Hong Kong Univ Sci & Technol Clear Water Bay Hong Kong Peoples R China Sungkyunkwan Univ Seoul South Korea

An automatic program repair (APR) technique is an implementation of a repair model to fix a given bug by modifying program behavior. Recently, repair models which collect source code and code changes from software history and use such collected resources for patch generation became more popular. Collected resources are used to expand the patch search space and to increase the probability that correct patches for bugs are included in the space. However, it is also revealed that navigation on such expanded patch search space is difficult due to the sparseness of correct patches in the space. In this study, we evaluate the effectiveness of Context-based Change Application (CCA) technique on change selection, fix location selection and change concretization, which are the key aspects of navigating patch search space. CCA collects abstract subtree changes and their AST contexts, and applies them to fix locations only if their contexts are matched. CCA repair model can address both search space expansion and navigation issues, by expanding search space with collected changes while narrowing down search areas in the search space based on contexts. Since CCA applies changes to a fix location only if their contexts are matched, it only needs to consider the same context changes for each fix location. Also, if there is no change with the same context as a fix location, this fix location can be ignored since it means that past patches did not modify such locations. In addition, CCA uses fine-grained changes preserving changed code structures, but normalizing user-defined names. Hence change concretization can be simply done by replacing normalized names with concrete names available in buggy code. We evaluated CCA's effectiveness with over 54K unique collected changes (221K in total) from about 5K human-written patches. Results show that using contexts, CCA correctly found 90.1% of the changes required for test set patches, while fewer than 5% of the changes were found without

关键词： automatic program repair Context-based change application repair models

来源：评论

学校读者我要写书评

暂无评论

METARO^(3):Metamorphic Relation Group for automatic program repair

引用

Computer Modeling in Engineering & Sciences 2019年第12期121卷 909-928页

作者： Tingting Wu Yunwei Dong School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’an710072China

The application of metamorphic testing(MT)on automatic program repair(APR-MT)is used to generate a patch without test oracles by examining whether the input metamorphic relation(MR)is satisfied or ***,the delivered patch is plausible since it may satisfy the input MR but violate other *** inspires us to propose an improved approach to enhance the effectiveness of APR-MT with metamorphic relation *** involves three major ***,we formally define the repair process of APR-MT by building the model of automatic program repair and metamorphic testing ***,we propose the advanced model of automatic program repair based on metamorphic relation group,named METARO^(3),which takes several MRs as input while only one MR is used in *** additionally present two kinds of selection strategies to rank MRs in descending order of the fault detection capability,which helps shorten the repair time of finding a *** demonstrate the feasibility and procedure of our approach,an illustration example was *** results show that METARO^(3) can improve the effectiveness of APR-MT significantly.

关键词： automatic program repair metamorphic testing metamorphic relation formal modeling

来源：评论

学校读者我要写书评

暂无评论

Applying Token Tagging to Augment Dataset for automatic program repair

引用

JOURNAL OF INFORMATION PROCESSING SYSTEMS 2022年第5期18卷 628-636页

作者： Hu, Huimin Lee, Byungjeong Univ Seoul Dept Comp Sci Seoul South Korea

automatic program repair (APR) techniques focus on automatically repairing bugs in programs and providing correct patches for developers, which have been investigated for decades. However, most studies have limitations in repairing complex bugs. To overcome these limitations, we developed an approach that augments datasets by utilizing token tagging and applying machine learning techniques for APR. First, to alleviate the data insufficiency problem, we augmented datasets by extracting all the methods (buggy and non-buggy methods) in the program source code and conducting token tagging on non-buggy methods. Second, we fed the preprocessed code into the model as an input for training. Finally, we evaluated the performance of the proposed approach by comparing it with the baselines. The results show that the proposed approach is efficient for augmenting datasets using token tagging and is promising for APR.

关键词： Augment Dataset automatic program repair Machine Learning Token Tagging

来源：评论

学校读者我要写书评

暂无评论

Improving Performance of automatic program repair using Learned Heuristics 2017

Improving Performance of Automatic Program Repair using Lear...

引用

11th Joint Meeting of European Software Engineering Conference (ESEC) / ACM SIGSOFT Symposium on the Foundations of Software Engineering (FSE)

作者： Schramm, Liam Bard Coll Annandale On Hudson NY 12504 USA

ISBN: (纸本)9781450351058

automatic program repair offers the promise of significant reduction in debugging time, but still faces challenges in making the process efficient, accurate, and generalizable enough for practical application. Recent efforts such as Prophet demonstrate that machine learning can be used to develop heuristics about which patches are likely to be correct, reducing overfitting problems and improving speed of repair. Searchrepair takes a different approach to accuracy, using blocks of human-written code as patches to better constrain repairs and avoid overfitting. This project combines Prophet's learning techniques with Searchrepair's larger block size to create a method that is both fast and accurate, leading to higher-quality repairs. We propose a novel first-pass filter to substantially reduce the number of candidate patches in Searchrepair and demonstrate 85% reduction in runtime over standard Searchrepair on the IntroClass dataset.

关键词： automatic program repair Machine learning Semantic search

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of automatic program repair Techniques for Security Vulnerabilities 32

A Comparative Study of Automatic Program Repair Techniques f...

引用

32nd IEEE International Symposium on Software Reliability Engineering (ISSRE)

作者： Pinconschi, Eduard Abreu, Rui Adao, Pedro INESC ID Lisbon Portugal ULisboa Inst Super Tecn Lisbon Portugal Univ Porto Porto Portugal Inst Telecomunicacoes Lisbon Portugal

ISBN: (纸本)9781665425872

In the past years, research on automatic program repair (APR), in particular on test-suite-based approaches, has significantly attracted the attention of researchers. Despite the advances in the field, it remains unclear how these techniques fare in the context of security-most approaches are evaluated using benchmarks of bugs that do not (only) contain security vulnerabilities. In this paper, we present our observations using 10 state-of-the-art test-suite-based automatic program repair tools on the DARPA Cyber Grand Challenge benchmark of vulnerabilities in C/C++. Our intention is to have a better understanding of the current state of automatic program repair tools when addressing security issues. In particular, our study is guided by the hypothesis that the efficiency of repair tools may not generalize to security vulnerabilities. We found that the 10 analyzed tools can only fix 30 out of 55 vulnerable programs-54.6% of the considered issues. In particular, we found that APR tools with atomic change operators and brute-force search strategy (AE and GenProg) and brute-force functionality deletion (Kali) overall perform better at repairing security vulnerabilities (considering both efficiency and effectiveness). AE is the tool that individually repairs most programs with 20 out of 55 programs (36.4%). The causes for failing to repair are discussed in the paper, which can help repair tool designers to improve their techniques and tools.

关键词： automatic program repair security vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：