Generative AI, particularly Large Language Models (LLMs), presents innovative opportunities to enhance softwareengineering education. Open source LLMs such as LLaMA and Mistral leverage the potential of generative AI...
详细信息
ISBN:
(纸本)9798350378986;9798350378979
Generative AI, particularly Large Language Models (LLMs), presents innovative opportunities to enhance softwareengineering education. Open source LLMs such as LLaMA and Mistral leverage the potential of generative AI offering distinct advantages over proprietary options including transparency, customizability, collaboration, and cost savings. This paper develops a catalog of LLM prompt examples tailored for softwareengineering training, mapped to knowledge areas from the softwareengineering Body of knowledge (SWEBoK) framework. Example prompts demonstrate LLMs' capabilities in eliciting requirements, diagram generation, API simulation, effort estimation through role-playing, and other areas. The methodology involves evaluating prompt responses from ChatGPT, Mistral, and LLaMA on representative tasks. Quantitative and qualitative analysis assesses quality, usefulness, and correctness. Findings show ChatGPT and Mistral outperforming LLaMA overall, but no model perfectly executes complex interactions. We examine implications and challenges of integrating open source LLMs into classrooms, emphasizing the need for oversight, verification, and prompt design aligned with pedagogical objectives.
The proceedings contain 6 papers. The topics discussed include: live software inspection and refactoring;machine-learning assisted model-implemented fault injection;multi-paradigm design space exploration for advanced...
The proceedings contain 6 papers. The topics discussed include: live software inspection and refactoring;machine-learning assisted model-implemented fault injection;multi-paradigm design space exploration for advanced cyber-physical systems;digital twins for continuous deployment in model-based systems engineering of cyber-physical systems;and a framework for integrating web accessibility requirements in agile methodology.
The proceedings contain 96 papers. The topics discussed include: feature selection in high-dimensional set-valued decision system;the TOPSIS method for multi-attribute group decision making with picture 2-tuple lingui...
ISBN:
(纸本)9798350318401
The proceedings contain 96 papers. The topics discussed include: feature selection in high-dimensional set-valued decision system;the TOPSIS method for multi-attribute group decision making with picture 2-tuple linguistic sets;temperature drift compensation of light scattering PM sensor based on bp neural network;predicting remaining useful life of lithium-ion battery using extended belief rule base model;a study of deep fuzzy clustering method based on maximum entropy clustering;a survey: navigating the landscape of incremental learning techniques and trends;a named entity recognition method for substation location selection;and a novel image encryption based on style transfer.
The proceedings contain 14 papers. The topics discussed include: investigating airplane crash data with watson analytics and Cognos analytics;a comparative analysis of the impact of Taobao image reviews on the sales o...
ISBN:
(纸本)9781450387866
The proceedings contain 14 papers. The topics discussed include: investigating airplane crash data with watson analytics and Cognos analytics;a comparative analysis of the impact of Taobao image reviews on the sales of search products and experience products;design and implementation of a distributed container-deployed web business traffic generator;research on the recognition of opinion leaders in social media based on social network analysis theory;dynamic android malware analysis with de-identification of personal identifiable information;an empirical study of multi-threading paradigms: reactive programming vs continuation-passing style;an annotated union catalog of local history resources on region 8: basis for an enhanced computerized database;and backpropagation neural network with feature sensitivity analysis: a pothole prediction model for flexible pavements using traffic and climate – associated factors.
The proceedings contain 29 papers. The special focus in this conference is on softwareengineering for Defence Applications. The topics include: Recruiting software Developers a Survey of Current Russian Practices;com...
ISBN:
(纸本)9783030146863
The proceedings contain 29 papers. The special focus in this conference is on softwareengineering for Defence Applications. The topics include: Recruiting software Developers a Survey of Current Russian Practices;comparison of Agile, Quasi-Agile and Traditional Methodologies;Innopolis Going Global: internationalization of a Young IT University;a Conjoint Application of Data Mining Techniques for Analysis of Global Terrorist Attacks: Prevention and Prediction for Combating Terrorism;game Theoretic Framework to Mutation Testing;a Survey on Code Analysis Tools for software Maintenance Prediction;stance Prediction for Russian: Data and Analysis;software Requirements Complexity Analysis to Support the “ADVISORY NETWORK IN TO THE NATION FORCES BUILD-UP”;hybrid Agile software Development for Smart Farming Application;detection of Inconsistent Contracts Through Modular Verification;evolving Diverse Cellular Automata Based Level Maps;balanced Map Generation Using Genetic Algorithms in the Siphon Board-Game;distributed Composition of Highly-Collaborative Services and Sensors in Tactical Domains;Safety and Security in GNU/Linux Real Time Operating System Domain;mapping Event-B Machines into Eiffel Programming Language;a Tool-Supported Approach for Building the Architecture and Roadmap in MegaM@Rt2 Project;the Key Role of Memory in Next-Generation Embedded Systems for Military Applications;vulnerabilities and Security Breaches in Cryptocurrencies;question-Answer Nets Objectifying a Conceptual Space in the Design of a System with software;on the Time Performance of Automated Fixes;on the Parcellation of Functional Magnetic Resonance Images;Affordance Theory Applied to Agile Development: A Case Study of LC2EVO;multi-level Security Approach on Weapon Systems.
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT E...
ISBN:
(纸本)9789819755004
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT Explanation;attention and Learning Features-Enhanced knowledge Tracing;An MLM Decoding Space Enhancement for Legal Document Proofreading;meta-pruning: Learning to Prune on Few-Shot Learning;knowledge-Informed Molecular Learning: A Survey on Paradigm Transfer;GenFlowchart: Parsing and Understanding Flowchart Using Generative AI;DSCVSR: A Lightweight Video Super-Resolution for Arbitrary Magnification;programming knowledge Tracing with Context and Structure Integration;an Konwledge-Based Semi-supervised Active Learning Method for Precision Pest Disease Diagnostic;multi-label Feature Selection with Adaptive Subspace Learning;User Story Classification with Machine Learning and LLMs;PTMA: Pre-trained Model Adaptation for Transfer Learning;optimization Strategies for knowledge Graph Based Distractor Generation;reinforced Subject-Aware Graph Neural Network for Related Work Generation;EFCC-IeT: Cross-Modal Electronic File Content Correlation via Image-Enhanced Text;multi-relation Neural Network Recommendation Model Based on knowledge Graph Embedding Algorithm;link Prediction Based on Deep Global Information in Heterogeneous Graph;subject knowledge Entity Relationship Extraction Based on Multi-feature Fusion and Relation Specific Horns Tagging;a Human-Computer Negotiation Model Based on Q-Learning;affine Transformation-Based knowledge Graph Embedding;integrating Prior Scenario knowledge for Composition Review Generation;distant Supervised Relation Extraction on Pre-train Model with Improved Multi-label Attention Mechanism;sEMG-Based Multi-view Feature-Constrained Representation Learning;vicinal Data Augmentation for Classification Model via Feature Weaken;STM: An Improved Peak Price Tracking-Based Online Portfolio Selection Algorithm;spatiotemporal Dependence Learning
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT E...
ISBN:
(纸本)9789819754977
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT Explanation;attention and Learning Features-Enhanced knowledge Tracing;An MLM Decoding Space Enhancement for Legal Document Proofreading;meta-pruning: Learning to Prune on Few-Shot Learning;knowledge-Informed Molecular Learning: A Survey on Paradigm Transfer;GenFlowchart: Parsing and Understanding Flowchart Using Generative AI;DSCVSR: A Lightweight Video Super-Resolution for Arbitrary Magnification;programming knowledge Tracing with Context and Structure Integration;an Konwledge-Based Semi-supervised Active Learning Method for Precision Pest Disease Diagnostic;multi-label Feature Selection with Adaptive Subspace Learning;User Story Classification with Machine Learning and LLMs;PTMA: Pre-trained Model Adaptation for Transfer Learning;optimization Strategies for knowledge Graph Based Distractor Generation;reinforced Subject-Aware Graph Neural Network for Related Work Generation;EFCC-IeT: Cross-Modal Electronic File Content Correlation via Image-Enhanced Text;multi-relation Neural Network Recommendation Model Based on knowledge Graph Embedding Algorithm;link Prediction Based on Deep Global Information in Heterogeneous Graph;subject knowledge Entity Relationship Extraction Based on Multi-feature Fusion and Relation Specific Horns Tagging;a Human-Computer Negotiation Model Based on Q-Learning;affine Transformation-Based knowledge Graph Embedding;integrating Prior Scenario knowledge for Composition Review Generation;distant Supervised Relation Extraction on Pre-train Model with Improved Multi-label Attention Mechanism;sEMG-Based Multi-view Feature-Constrained Representation Learning;vicinal Data Augmentation for Classification Model via Feature Weaken;STM: An Improved Peak Price Tracking-Based Online Portfolio Selection Algorithm;spatiotemporal Dependence Learning
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT E...
ISBN:
(纸本)9789819754915
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT Explanation;attention and Learning Features-Enhanced knowledge Tracing;An MLM Decoding Space Enhancement for Legal Document Proofreading;meta-pruning: Learning to Prune on Few-Shot Learning;knowledge-Informed Molecular Learning: A Survey on Paradigm Transfer;GenFlowchart: Parsing and Understanding Flowchart Using Generative AI;DSCVSR: A Lightweight Video Super-Resolution for Arbitrary Magnification;programming knowledge Tracing with Context and Structure Integration;an Konwledge-Based Semi-supervised Active Learning Method for Precision Pest Disease Diagnostic;multi-label Feature Selection with Adaptive Subspace Learning;User Story Classification with Machine Learning and LLMs;PTMA: Pre-trained Model Adaptation for Transfer Learning;optimization Strategies for knowledge Graph Based Distractor Generation;reinforced Subject-Aware Graph Neural Network for Related Work Generation;EFCC-IeT: Cross-Modal Electronic File Content Correlation via Image-Enhanced Text;multi-relation Neural Network Recommendation Model Based on knowledge Graph Embedding Algorithm;link Prediction Based on Deep Global Information in Heterogeneous Graph;subject knowledge Entity Relationship Extraction Based on Multi-feature Fusion and Relation Specific Horns Tagging;a Human-Computer Negotiation Model Based on Q-Learning;affine Transformation-Based knowledge Graph Embedding;integrating Prior Scenario knowledge for Composition Review Generation;distant Supervised Relation Extraction on Pre-train Model with Improved Multi-label Attention Mechanism;sEMG-Based Multi-view Feature-Constrained Representation Learning;vicinal Data Augmentation for Classification Model via Feature Weaken;STM: An Improved Peak Price Tracking-Based Online Portfolio Selection Algorithm;spatiotemporal Dependence Learning
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT E...
ISBN:
(纸本)9789819754946
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT Explanation;attention and Learning Features-Enhanced knowledge Tracing;An MLM Decoding Space Enhancement for Legal Document Proofreading;meta-pruning: Learning to Prune on Few-Shot Learning;knowledge-Informed Molecular Learning: A Survey on Paradigm Transfer;GenFlowchart: Parsing and Understanding Flowchart Using Generative AI;DSCVSR: A Lightweight Video Super-Resolution for Arbitrary Magnification;programming knowledge Tracing with Context and Structure Integration;an Konwledge-Based Semi-supervised Active Learning Method for Precision Pest Disease Diagnostic;multi-label Feature Selection with Adaptive Subspace Learning;User Story Classification with Machine Learning and LLMs;PTMA: Pre-trained Model Adaptation for Transfer Learning;optimization Strategies for knowledge Graph Based Distractor Generation;reinforced Subject-Aware Graph Neural Network for Related Work Generation;EFCC-IeT: Cross-Modal Electronic File Content Correlation via Image-Enhanced Text;multi-relation Neural Network Recommendation Model Based on knowledge Graph Embedding Algorithm;link Prediction Based on Deep Global Information in Heterogeneous Graph;subject knowledge Entity Relationship Extraction Based on Multi-feature Fusion and Relation Specific Horns Tagging;a Human-Computer Negotiation Model Based on Q-Learning;affine Transformation-Based knowledge Graph Embedding;integrating Prior Scenario knowledge for Composition Review Generation;distant Supervised Relation Extraction on Pre-train Model with Improved Multi-label Attention Mechanism;sEMG-Based Multi-view Feature-Constrained Representation Learning;vicinal Data Augmentation for Classification Model via Feature Weaken;STM: An Improved Peak Price Tracking-Based Online Portfolio Selection Algorithm;spatiotemporal Dependence Learning
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT E...
ISBN:
(纸本)9789819754885
The proceedings contain 160 papers. The special focus in this conference is on knowledge Science, engineering and Management. The topics include: EE-LCE: An Event Extraction Framework Based on LLM-Generated CoT Explanation;attention and Learning Features-Enhanced knowledge Tracing;An MLM Decoding Space Enhancement for Legal Document Proofreading;meta-pruning: Learning to Prune on Few-Shot Learning;knowledge-Informed Molecular Learning: A Survey on Paradigm Transfer;GenFlowchart: Parsing and Understanding Flowchart Using Generative AI;DSCVSR: A Lightweight Video Super-Resolution for Arbitrary Magnification;programming knowledge Tracing with Context and Structure Integration;an Konwledge-Based Semi-supervised Active Learning Method for Precision Pest Disease Diagnostic;multi-label Feature Selection with Adaptive Subspace Learning;User Story Classification with Machine Learning and LLMs;PTMA: Pre-trained Model Adaptation for Transfer Learning;optimization Strategies for knowledge Graph Based Distractor Generation;reinforced Subject-Aware Graph Neural Network for Related Work Generation;EFCC-IeT: Cross-Modal Electronic File Content Correlation via Image-Enhanced Text;multi-relation Neural Network Recommendation Model Based on knowledge Graph Embedding Algorithm;link Prediction Based on Deep Global Information in Heterogeneous Graph;subject knowledge Entity Relationship Extraction Based on Multi-feature Fusion and Relation Specific Horns Tagging;a Human-Computer Negotiation Model Based on Q-Learning;affine Transformation-Based knowledge Graph Embedding;integrating Prior Scenario knowledge for Composition Review Generation;distant Supervised Relation Extraction on Pre-train Model with Improved Multi-label Attention Mechanism;sEMG-Based Multi-view Feature-Constrained Representation Learning;vicinal Data Augmentation for Classification Model via Feature Weaken;STM: An Improved Peak Price Tracking-Based Online Portfolio Selection Algorithm;spatiotemporal Dependence Learning
暂无评论