Search Results for « Large Language Models (LLMs) »

We will introduce Large Language Models (LLMs), focusing on their core architecture, training methodologies, practical applications, and some important considerations. We begin with a brief exploration of the transformer architecture, examining how architectural choices and scaling laws have shaped modern language models. We then investigate key training paradigms, with particular emphasis on Reinforcement Learning from Human Feedback (RLHF) and instruction tuning, while briefly touching on emerging approaches like Direct Preference Optimisation (DPO). The discussion progresses through the evolution of knowledge integration techniques, from basic context stuffing to Retrieval-Augmented Generation (RAG), highlighting their practical implications. We will discuss the critical issue of hallucinations in LLM outputs, providing concrete examples and verification strategies. To conclude, a quick overview of the current software landscape and immediate future developments in the field, and a look ahead to the rest of the webinar series.

In recent months, I have been watching with a mix of trepidation and curiosity as the introduction of Large language models (LLMs) has become mainstream in academic research and technical development. As a practitioner and educator in systems engineering and mechanical design, it is my responsibility to keep my knowledge and skill set up-to-date and reflect this in my research and teaching. Part of this includes evaluating new tools and technology within my area of expertise and providing realistic professional guidance based on my experiences. This reflection outlines my thoughts and professional opinion on the use of LLMs to support systems engineering and mechanical design. As a designer with training in classic mathematical optimization techniques and large-scale systems engineering, I first worked to understand LLMs and how they relate to my area of expertise in systems engineering and mechanical design. From an engineering perspective, an LLM is an artificial intelligence (AI) or optimization model which has been designed and trained using human language. Similar to how most of these kinds of tools are trained using labeled images or real-world technical data, LLMs recognize patterns and interactions between words and pieces of written text. The initial models are only as good as their training data, but continue to improve over time as they encounter more and more data. As with many other types of AI models, the initial training is done with a massive dataset (text in the case of LLMs) using an unsupervised learning algorithm. Once the baseline model is trained using the general dataset, it can then be refined using more specialized training data to develop more specialized tools. It is clear that LLMs are not some kind of new technology or “silver bullet” tool but simply a different application and logical progression/development of existing design and AI tools which derive from classic mathematical optimization. This is reassuring for those nervous about the emergence of a technology which seems to blur the lines between human and machine. In reality, it is simply a mathematical model which mimics human speech and writing by learning patterns.

Do Large Language Models have cognitive abilities? Do Large Language Models have understanding? Is the correct recognition of verbal contexts or visual objects, based on pre-learning on a large training dataset, a manifestation of the ability to solve cognitive tasks? Or is any LLM just a statistical approximator that compiles averaged texts from its huge dataset close to the specified prompts? The answers to these questions require rigorous formal definitions of the cognitive concepts of "knowledge", "understanding" and related terms.

Disaster recovery (DR) is a critical component of any organization's cloud strategy, ensuring business continuity during catastrophic events. This paper provides an in-depth exploration of various DR strategies available within Amazon Web Services (AWS), including Backup and Restore, Pilot Light, Warm Standby, and Multi-Site Active/Active. We focus on optimizing Recovery Time Objective (RTO) and Recovery Point Objective (RPO) for critical workloads while balancing cost and complexity. The paper also explores integrating AWS-native services with cutting-edge automation techniques to ensure a robust disaster recovery solution that aligns with business continuity plans.

Understanding the Evolutionary Journey of LLMs Author Wenyi Pi ( <strong> ORCID </strong> : 0009–0002–2884–2771) Introduction When we talk about large language models (LLMs), we are actually referring to a type of advanced software that can communicate in a human-like manner. These models have the amazing ability to understand complex contexts and generate content that is coherent and has a human feel.

The rapid growth of Large Language Models (LLMs) has revolutionized business operations across sectors such as finance, healthcare, customer service, and more. These models are no longer experimental but are becoming core components in streamlining workflows and decision-making. However, the integration of LLMs brings new challenges: ensuring the accuracy of outputs, monitoring model performance, and maintaining strict compliance with industry regulations[1]. This white paper provides an in-depth review of leading LLM tracing and evaluation tools, examining their strengths, limitations, and relevance for real-world use cases. We aim to guide organizations in choosing the right tools to enhance model performance, ensure compliance with data security protocols, and generate actionable insights.

Understanding the Evolutionary Journey of LLMs Author Wenyi Pi ( <strong> ORCID </strong> : 0009–0002–2884–2771) Introduction When we talk about large language models (LLMs), we are actually referring to a type of advanced software that can communicate in a human-like manner. These models have the amazing ability to understand complex contexts and generate content that is coherent and has a human feel.