检索结果-内蒙古大学图书馆

Source Code Summarization in the Era of Large Language Models

学校读者我要写书评

暂无评论

Source Code Summarization in the Era of Large Language Model...

International Conference on Software Engineering (ICSE)

作者： Weisong Sun Yun Miao Yuekang Li Hongyu Zhang Chunrong Fang Yi Liu Gelei Deng Yang Liu Zhenyu Chen College of Computing and Data Science Nanyang Technological University Singapore Singapore State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering University of New South Wales Sidney Australia School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798331505691

ISBN: (纸本)9798331505707

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of coderelated tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLMbased code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs' model settings (including top_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs' abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types (e.g., procedural and object-oriented programming languages). Finally, we unexpectedly find that CodeLlamaInstruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code design rationale and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of LLMs.

关键词： Computer languages Codes Systematics Source coding Large language models object oriented modeling Software Prompt engineering object oriented programming Software engineering

Enhancing Spectrum-Based Fault Localization in the Context of Reactive programming

学校读者我要写书评

暂无评论

Enhancing Spectrum-Based Fault Localization in the Context o...

International Conference on Software Testing, Verification, and Validation, ICST

作者： Aondowase James Orban Software Engineering Department University of Szeged Szeged Hungary

ISBN: (数字)9798331508142

ISBN: (纸本)9798331508159

Several research works have been performed on the spectrum-based fault localization (SBFL) technique that aims to identify and isolate suspicious errors during software development in traditional programming paradigms such as imperative and object-oriented programming. After extensive research, I noticed that there seem to be few research works that connect SBFL and reactive programming. Since reactive programming is centered on data streams and the propagation of changes where states are updated asynchronously in response to external stimuli, the traditional coverage-based spectrum seems to be less appropriate for reactive programs. Having considered these limitations, my aim is to investigate and develop a new technique to apply and enhance the traditional SBFL for reactive programming. In this doctoral symposium, I present my research topic, the relevant research questions based on the topic, and outline some plans to be considered in the remaining period of my PhD research work.

关键词： Location awareness Software testing Fault diagnosis External stimuli Medical services programming object recognition object oriented programming Streams Software development management

Evaluating the Dependency Between Cyclomatic Complexity and Response For Class

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Stavtsev, Maxim Bugayenko, Yegor Higher School of Economics Moscow Russia Huawei Moscow Russia

In object-oriented programming, it is reasonable to hypothesize that smaller classes with fewer methods are less complex. Should this hypothesis hold true, it would be advisable for programmers to design classes with fewer methods, as complexity significantly contributes to poor maintainability. To test this assumption, we analyzed 862,517 Java classes from 1,000 open GitHub repositories. Our findings indicate a strong Pearson correlation of 0.79 between the cumulative McCabe’s Cyclomatic Complexity (CC) of all class methods and the number of methods, a metric known as Response for Class (RFC). © 2024, CC BY.

关键词： object oriented programming

Structuring and Integrating Smart Building Planning Rules With BIM-based Planning Tools

学校读者我要写书评

暂无评论

Structuring and Integrating Smart Building Planning Rules Wi...

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： Markus Aleksy Philipp Bauer ABB Corporate Research Center Mannheim Germany

ISBN: (数字)9798331527198

ISBN: (纸本)9798331527204

Modern building automation systems are subject to major challenges. Their architecture becomes increasingly diversified. Recent developments, such as increased digitization and Internet of Things (IoT) enable new implementation and application opportunities. The main modeling method regarding the development and management of digital representations of physical and functional characteristics of buildings is referred to Building Information Modeling (BIM).In this paper, we describe how planning rules sets from existing tools can be split, structured, and integrated with established external BIM-based building planning tools to improve the collaboration between various trades. In our case study, we utilized Autodesk Revit as an example of a BIM-based planning tool that can be used for the proposed integration approach.

关键词： Smart buildings object oriented modeling Focusing Collaboration Software Extensibility Planning Internet of Things object oriented programming Engines

Oversight in Action: Experiences with Instructor-Moderated LLM Responses in an Online Discussion Forum

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qiao, Shuying Denny, Paul Giacaman, Nasser University of Auckland Auckland New Zealand

The integration of large language models (LLMs) into computing education offers many potential benefits to student learning, and several novel pedagogical approaches have been reported in the literature. However LLMs also present challenges, one of the most commonly cited being that of student over-reliance. This challenge is compounded by the fact that LLMs are always available to provide instant help and solutions to students, which can undermine their ability to independently solve problems and diagnose and resolve errors. Providing instructor oversight of LLM-generated content can mitigate this problem, however it is often not practical in real-time learning contexts. Online class discussion forums, which are widely used in computing education, present an opportunity for exploring instructor oversight because they operate asynchronously. Unlike real-time interactions, the discussion forum format aligns with the expectation that responses may take time, making oversight not only feasible but also pedagogically appropriate. In this practitioner paper, we present the design, deployment, and evaluation of a ‘bot’ module that is controlled by the instructor, and integrated into an online discussion forum. The bot assists the instructor by generating draft responses to student questions, which are reviewed, modified, and approved before release. Key features include the ability to leverage course materials, access archived discussions, and publish responses anonymously to encourage open participation. We report our experiences using this tool in a 12-week second-year software engineering course on object-oriented programming. Instructor feedback confirmed the tool successfully alleviated workload but highlighted a need for improvement in handling complex, context-dependent queries. We report the features that were viewed as most beneficial, and suggest avenues for future exploration. Copyright © 2024, The Authors. All rights reserved.

关键词： object oriented programming

Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhu, Xiaomeng Li, Yuyang Cui, Leiyao Li, Pengfei Gao, Huan-Ang Zhu, Yixin Zhao, Hao Institute for Artificial Intelligence Peking University Beijing100091 China Department of Computer Science and Engineering Hong Kong University of Science and Technology 999077 Hong Kong Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institute for Al Industry Research Tsinghua University Beijing100084 China Department of Computer Science Tsinghua University Beijing100084 China

object affordance reasoning, the ability to infer object functionalities based on physical properties, is fundamental for task-oriented planning and activities in both humans and Artificial Intelligence (AI). This capability, required for planning and executing daily activities in a task-oriented manner, relies on commonsense knowledge of object physics and functionalities, extending beyond simple object recognition. Current computational models for affordance reasoning from perception lack generalizability, limiting their applicability in novel scenarios. Meanwhile, comprehensive Large Language Models (LLMs) with emerging reasoning capabilities are challenging to deploy on local devices for task-oriented manipulations. Here, we introduce LVIS-Aff, a large-scale dataset comprising 1,496 tasks and 119k images, designed to enhance the generalizability of affordance reasoning from perception. Utilizing this dataset, we develop Afford-X, an end-to-end trainable affordance reasoning model that incorporates Verb Attention and Bi-Fusion modules to improve multi-modal understanding. This model achieves up to a 12.1% performance improvement over the best-reported results from non-LLM methods, while also demonstrating a 1.2% enhancement compared to our previous conference paper. Additionally, it maintains a compact 187M parameter size and infers nearly 50 times faster than the GPT-4V API. Our work demonstrates the potential for efficient, generalizable affordance reasoning models that can be deployed on local devices for task-oriented manipulations. We showcase Afford-X’s effectiveness in enabling task-oriented manipulations for robots across various tasks and environments, underscoring its efficiency and broad implications for advancing robotics and AI systems in real-world applications. © 2025, CC BY.

关键词： object oriented programming

Multidisciplinary Design Optimisation of UAVs: Conceptual Design of a MATLAB-Based Framework

学校读者我要写书评

暂无评论

Multidisciplinary Design Optimisation of UAVs: Conceptual De...

Research, Invention, and Innovation Congress (RI2C)

作者： Natee Tanman Douglas Thomson David Anderson James Watt School of Engineering University of Glasgow Glasgow the United Kingdom

ISBN: (数字)9798331506018

ISBN: (纸本)9798331506025

Unmanned Aerial Vehicles (UAVs) have been utilised as critical tools in a wide range application from military to civilian purposes. Designing UAVs involves interactions between various subsystems such as aerodynamics, structures and propulsion. In order to tackle the complexity of such interactions, a multidisciplinary design optimisation (MDO) approach can then be used to achieve an optimisation of the entire UAV system. This paper presents a conceptual design of a MDO framework for UAVs developed in MATLAB. The proposed framework integrates various disciplines enhancing the ability to conduct comprehensive multidisciplinary design analysis. A key feature of this framework is the use of object-oriented programming (OOP) which establishes the organisation and management of all data and processes. As for the case studies, a simple example was applied to demonstrate the reliability of the proposed methodology. The second example case was a more complex scenario focusing on the optimal design of a battery-powered Vertical Take-Off and Landing (VTOL) UAV using low-fidelity models. The results from these case studies showed that the proposed MDO architecture performed well and provided valuable insights into UAV design optimisation.

关键词： Technological innovation object oriented modeling Rotors Propulsion Autonomous aerial vehicles Robustness Complexity theory MATLAB object oriented programming Optimization

Data Spatial programming

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Mars, Jason University of Michigan 2260 Hayward St. Ann ArborMI48104 United States

We introduce a novel programming model, Data Spatial programming, which extends the semantics of object-oriented programming (OOP) by introducing new class-like constructs called archetypes. These archetypes encapsulate the topological relationships between data entities and the execution flow in a structured manner, enabling more expressive and semantically rich computations over interconnected data structures or finite states. By formalizing the relationships between data elements in this topological space, our approach allows for more intuitive modeling of complex systems where a topology of connections is formed for the underlying computational model. This paradigm addresses limitations in traditional OOP when representing a wide range of problems in computer science such as agent-based systems, social networks, processing on relational data, neural networks, distributed systems, finite state machines, and other spatially-oriented computational problems. © 2025, CC BY-NC-ND.

关键词： object oriented programming

Reframing Cognition: A Multilayered Approach to Expertise and Artificial Intelligence

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Conversano, Simone University of Pisa Via Francesco Bonaini 44 Pisa56125 Italy

The concept of cognition is central to many disciplines, such as psychology, neuroscience, Artificial Intelligence, and philosophy of mind. Despite some divergent perspectives, cognition is defined in a strictly biochemical framework, and considered possible almost solely in embodied, living agents. This is due to the absence of conclusive evidence that cognition is possible without the neurochemical and sociobiological relationship between brain, body, and environment typical of animals and humans (embodied embedded cognition and situated cognition). Since human expertise is closely dependent on cognition, and AI is evidently expert without being properly cognitive, in this paper we explore the possibility of extending the concept of cognition to encompass both biological and artificial agents. By studying the correlations between expertise, intelligence, and agency, we attempt to reduce the minimum properties required to define cognition by introducing a framework in which the general cognition also includes currently unknown forms of cognition. Following naive set theory, knowledge representation notation and object-oriented programming, we will therefore formalize a General Cognition class (CG), which has Biological Cognition (CB) and Nonbiological Cognition (CNB) as its subclasses, while considering the epistemic and scientific problems and opportunities of this perspective, which we will explore in the future. © 2024, The Authors. All rights reserved.

关键词： object oriented programming