Related papers: Knowledge Lever Risk Management for Software Engin…
This paper introduces Self-aware Knowledge Retrieval (SeaKR), a novel adaptive RAG model that extracts self-aware uncertainty of LLMs from their internal states. SeaKR activates retrieval when the LLMs present high self-aware uncertainty…
Multi-agent large language model (LLM) systems are rapidly emerging as the dominant architecture for enterprise AI automation, yet production deployments exhibit failure rates between 41% and 86.7%, with nearly 79% of failures originating…
Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM platforms, and time-consuming manual triage workflows. We present an end-to-end threat…
Machine learning (ML) techniques increase the effectiveness of software engineering (SE) lifecycle activities. We systematically collected, quality-assessed, summarized, and categorized 83 reviews in ML for SE published between 2009-2022,…
In recent years, there has been growing interest in leveraging the impressive generalization capabilities and reasoning ability of large language models (LLMs) to improve the performance of recommenders. With this operation, recommenders…
This research considers the impact of social engineering security attacks which are noted as taking opportunities for critically exploiting user awareness and behavior. The research proposes in this respect a managerial method in an attempt…
In the product business still battles with the hard assignment of creating programming applications that meet quality gauges, and spending limitations. The requirement for programming to be without mistake remained a test to the IT…
Increased usage of the internet has contributed immensely to the growth of software development practice in East Africa. This paper investigates the existence of formal KM (Knowledge Management) initiatives in the Software industry such as…
Repository-level code comprehension and knowledge sharing remain core challenges in software engineering. Large language models (LLMs) have shown promise by generating explanations of program structure and logic. However, these approaches…
Context: Voluntary turnover is common in the software industry, increasing recruitment and onboarding costs and the risk of losing organizational and tacit knowledge. Objective: This study investigates how job satisfaction, work-life…
Knowledge engineering is a discipline that focuses on the creation and maintenance of processes that generate and apply knowledge. Traditionally, knowledge engineering approaches have focused on knowledge expressed in formal languages. The…
Companies that develop software have a pressure from customers to deliver better solutions, and to deliver solutions faster and cheaper. Many researchers have worked with suggestions on how to improve the development process; software…
Knowledge Management (KM) is a strategic component that enables development, growth and continuous improvement of Public Sector Organizations (PSO). This thesis is bounded to this specific context. Indeed, we critically and comprehensively…
The integration of large language models (LLMs) into robotic task planning has unlocked better reasoning capabilities for complex, long-horizon workflows. However, ensuring safety in LLM-driven plans remains a critical challenge, as these…
Knowledge has been lately recognized as one of the most important assets of organizations. Managing knowledge has grown to be imperative for the success of a company. This paper presents an overview of Knowledge Management and various…
Applying LLM-based multi-agent software systems in safety-critical domains such as lifespan echocardiography introduces system-level risks that cannot be addressed by improving model accuracy alone. During system operation, beyond…
Systematic Literature Review (SLR) is a rigorous methodology applied for Evidence-Based Software Engineering (EBSE) that identify, assess and synthesize the relevant evidence for answering specific research questions. Benefiting from the…
To reduce the computation cost and the energy consumption in large language models (LLM), skimming-based acceleration dynamically drops unimportant tokens of the input sequence progressively along layers of the LLM while preserving the…
Release engineering has traditionally focused on continuously delivering features and bug fixes to users, but at a certain scale, it becomes impossible for a release engineering team to determine what should be released. At Meta's scale,…
Given the data-intensive and collaborative trend in science, the software engineering community also pays increasing attention to obtaining valuable and useful insights from data repositories. Nevertheless, applying data science to software…