The dynamic knowledge graph is a data structure that adds temporal information to the nodes and edges of a traditional knowledge graph. It describes the changing processes of entities and relationships over time, ther...
详细信息
Large language models (LLMs) based on transformer architecture have revolutionized natural language processing (NLP), demonstrating excellent capabilities in understanding and generating human-like text. In software E...
详细信息
ISBN:
(纸本)9783031808883;9783031808890
Large language models (LLMs) based on transformer architecture have revolutionized natural language processing (NLP), demonstrating excellent capabilities in understanding and generating human-like text. In softwareengineering, LLMs have been applied in code generation, documentation, and report writing tasks, to support the developer and reduce the amount of manual work. In software Testing, one of the cornerstones of softwareengineering, LLMs have been explored for generating test code, test inputs, automating the oracle process or generating test scenarios. However, their application to high-level testing stages such as system testing, in which a deep knowledge of the business and the technological stack is needed, remains largely unexplored. This paper presents an exploratory study about how LLMs can support system test development. Given that LLM performance depends on input data quality, the study focuses on how to query general purpose LLMs to first obtain test scenarios and then derive test cases from them. The study evaluates two popular LLMs (GPT-4o and GPT-4o-mini), using as a benchmark a European project demonstrator. The study compares two different prompt strategies and employs well-established prompt patterns, showing promising results as well as room for improvement in the application of LLMs to support system testing.
This contribution delves into the incorporation of Sustainable Development Goals (SDGs) into the Computer engineering curriculum. The study addresses challenges associated with integrating SDGs as cross-cutting conten...
详细信息
This paper aims to comprehensively examine diverse knowledge switch techniques used in scientific photograph segmentation with deep mastery. Specifically, we know the latest advances in transfer, gaining knowledge of ...
详细信息
The reform of the Approval Process of Construction Projects (APCP) is part of the broader reform of the administrative approval system in the construction sector. This reform is a crucial step in transforming governme...
详细信息
In edge-cloud systems, the quality of infrastructure deployment is crucial for delivering high-quality services, especially when using popular Infrastructure as Code (IaC) tools like Ansible. Ensuring the reliability ...
详细信息
ISBN:
(纸本)9783031751097;9783031751103
In edge-cloud systems, the quality of infrastructure deployment is crucial for delivering high-quality services, especially when using popular Infrastructure as Code (IaC) tools like Ansible. Ensuring the reliability of such large-scale code systems poses a significant challenge due to the limited testing resources. software defect prediction (SDP) addresses this limitation by identifying defectprone software modules, allowing developers to prioritize testing resources effectively. This paper introduces a Large Language Model (LLM)-based approach for SDP in Ansible scripts with Code-Smell-guided Prompting (CSP). CSP leverages code smell indicators extracted from Ansible scripts to refine prompts given to LLMs, enhancing their understanding of code structure concerning defects. Our experimental results demonstrate that CSP variants, particularly the Chain of Thought CSP (CoT-CSP), outperform traditional prompting strategies, as evidenced by improved F1-scores and Recall. To the best of our knowledge, this is the first attempt to employ LLMs for SDP in Ansible scripts. By employing a code smell-guided prompting strategy tailored for Ansible, we anticipate that the proposed method will enhance software quality assurance and reliability, thereby increasing the overall reliability of edge-cloud systems.
The proceedings contain 40 papers. The special focus in this conference is on Database and Expert Systems Applications. The topics include: Synthetic Data in Automatic Number Plate Recognition;An Untold Tale of...
ISBN:
(纸本)9783031143427
The proceedings contain 40 papers. The special focus in this conference is on Database and Expert Systems Applications. The topics include: Synthetic Data in Automatic Number Plate Recognition;An Untold Tale of Scientific Collaboration: SCCH and AC 2 T;on the Creation and Maintenance of a Documentation Generator in an Applied Research Context;towards the Digitalization of Additive Manufacturing;Twenty Years of Successful Translational Research: A Case Study of Three COMET Centers;data Integration, Management, and Quality: From Basic Research to Industrial Application;building a YouTube Channel for Science Communication;introduction of Visual Regression Testing in Collaboration Between Industry and Academia;vibration Analysis for Rotatory Elements Wear Detection in Paper Mill Machine;applying Time-Inhomogeneous Markov Chains to Math Performance Rating;introducing Data Science Techniques into a Company Producing Electrical Appliances;a Technology Transfer Portal to Promote Industry-Academia Collaboration in South-Tyrol;fast and Automatic Object Registration for Human-Robot Collaboration in Industrial Manufacturing;sending Spies as Insurance Against Bitcoin Pool Mining Block Withholding Attacks;risks in DeFi-Lending Protocols - An Exploratory Categorization and Analysis of Interest Rate Differences;battling the Bullwhip Effect with Cryptography;Reporting of Cross-Border Transactions for Tax Purposes via DLT;securing File System Integrity and Version History Via Directory Merkle Trees and Blockchains;taxation of Blockchain Staking Rewards: Propositions based on a Comparative Legal Analysis;comparison Framework for Blockchain Interoperability Implementations;A Comparative Analysis of Anomaly Detection Methods for Predictive Maintenance in SME;towards Strategies for Secure Data Transfer of IoT Devices with Limited Resources;application of Validation Obligations to Security Concerns;mode Switching for Secure Edge Devices;a Lifecycle Framework for Semantic Web Machine Learn
Given the presence of residual vulnerabilities in software systems, it is critical to apply suitable countermeasures in order to minimize the likelihood of an attack. In this paper we propose a formal approach, based ...
详细信息
The identification of real and fake news has become difficult task in the recent years due to more similar feature between them. As the issues of fake news are leading the miscommunication to the reads, various automa...
详细信息
Soldering irons are a hand tool that is indispensable in the process of making small series of electronic devices. Soldering irons have evolved from very simple devices without temperature control to devices with comp...
详细信息
暂无评论