Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 256 for “"Large language model (LLM)"”.
-
Exploring the role of large language model (LLM)-based chatbots for human resources
… cultivated a fertile ground for the expansion of large-scale language models. The rise of large language model-based chatbots stems from their ability to comprehend and respond to human input, offering detailed information, addressing inquiries, and aiding in various tasks. The emergence of …
-
Real-Time Data Informed Traffic Analytics Framework Powered by Large Language Model (LLM)
… The complexities associated with querying large-scale multi-table databases require specialized programming expertise and labor-intensive development. Additionally, traditional analysis methods have focused mainly on numerical data, often neglecting the semantic aspects that could enhance …
-
Large Language Model (LLM)-Based Health Coaches in Virtual Reality (VR) : Effects of AI Agents’ Nonverbal Behavior on Rapport and Health Outcomes
Thesis (Ph.D.)--Michigan State University. Communication - Doctor of Philosophy, 2025
-
Large Language Models for Build System Maintenance: An Empirical Study of CodeGen’s Next-Line Prediction
… In this thesis, I explore whether applying a Large Language Model (LLM) can reduce the burden of maintaining build systems. I aim to determine whether the prior content in build specifications provides sufficient context for an LLM to generate subsequent lines accurately. I conduct an …
-
Low Melting Temperatures Glasses for Lunar Applications Using Additive Manufacturing Process
large language model (LLM) with melting temperatures below 1000C. Some compositions of B2O3-Bi2O3-CaO were synthesis using melt-quench method under normal lab conditions. Synthesized samples were successfully melted below 1000C with amorphous microstructure, good thermal stabilities and high …
-
Understanding The Challenges with Using Hardware Pre-Fetchers for CPU-Based Matrix Multiply Units
… Unit (GPU) being the de facto standard of large scale matrix computation accelerator. This work aims to answer questions about how difficult it is to use the traditional Central Processing Unit (CPU) with matrix accelerators and prefetching hardware integrated into the core instruction set …
-
Dirbtinio intelekto agentinės sistemos prototipo kūrimas testų kokybei užtikrinti /
… generates unit and component tests using a large language model (LLM), validates the generated tests, and only then runs Stryker.NET mutation testing as the final quality measurement. The system was evaluated on three C# classes: one purelogic class and two service classes with dependency …
-
Implicit pen annotation assisted by Large Language Models
… tool with a digital pen. It leverages a Large Language Model (LLM) (1) to infer the underlying purposes of the user’s annotations and (2) automatically generates annotations with the same purpose throughout the document. AnnotateGPT aims to alleviate the burdens of manual annotation, …
-
FROM FAMILY INTERACTION TO DYNAMIC FEEDBACK:ADVANCES IN MANDARIN LANGUAGE LEARNING APPLICATIONS
… is vital as Singapore's second most spoken language, but pronunciation training remains underrepresented in learning. This thesis covers two Computer-Assisted Language Learning (CALL) projects enhancing Mandarin acquisition. The first focuses on a tablet app for children and parents, using …
-
Edukacinio turinio kūrimas naudojant dirbtinį intelektą /
… dependency graphs. Since it was decided to use a large language model (LLM) to develop this application, a literature review and a comparative analysis of LLMs were carried out. It concluded that Gemini (Ultra) is the superior LLM. Nevertheless, Gemini 1.5 Pro was chosen for formula recognition in …
-
Real-time Relevance: RAG with Dynamic Context for Improved Natural Language Responses
… In this thesis we investigate an autoregressive Large Language Model (LLM) architecture which can generate a real-time relevant dense search vector for every token generation step. To facilitate this we also develop a synthetic data generation technique to acquire search query vector labels on a …
-
AUDITING LARGE LANGUAGE MODELS: ACCOUNTABILITY, INTEGRITY, AND COPYRIGHT
This thesis addresses critical Large Language Model (LLM) governance challenges by proposing three technical solutions. First, to enhance content traceability, we introduce a novel watermarking method based on pseudo-random segment assignment, achieving superior extraction accuracy and time …
-
Toward automated requirements engineering: empirical and architectural foundations for structured parsing and knowledge discovery
… Engineering (RE) relies heavily on natural language, which is often vague, inconsistently structured, and difficult to automate reliably. This thesis presents TRAC-RE, a Traceable, Reliable, Auditable, and Contextual framework for automated requirements engineering. The framework consists of …
-
Cyberbullying Defensive Strategy in Social Media Sessions via Machine Learning and Cyber Deception
… proposes an integrated framework that combines large language model (LLM)-based detection with generative decoy responses to enable real-time protection for victims on platforms like Instagram and WhatsApp. Using models such as Mistral 7B, GPT-3.5 Turbo, and Phi-3 Mini, prompt-based one-shot …
-
Housekeep: Tidying Virtual Households using Commonsense Reasoning
… and navigation. It leverages a fine-tuned large language model (LLM) trained on an internet text corpus for effective planning. See our webpage for code, data and more details: https://yashkant.github.io/housekeep/. We find that our baseline planner generalizes to some extent when …
-
AI Retrieval-Augmented Generation (RAG) System with Engineering Document Information Extraction for Employee Development
This paper explores the implementation of AI large language model (LLM) support systems that utilize retrieval-augmented generation (RAG) to enhance employee effectiveness in trouble-shooting on a manufacturing production line. The RAG-augmented LLM tool is designed to ex-tract relevant data from …
-
RETHINKING INDUSTRY CLASSIFICATION: LEVERAGING LLMS FOR MULTI-VIEW AND MULTI-LABEL APPROACHES
… product markets. This dissertation develops two large language model (LLM)-aided, unsupervised approaches to produce more economically meaningful industry representations. The first study introduces a multi-view graph clustering framework integrating business descriptions from SEC 10-K filings, …
-
LLM-powered active learning for cost-effective text classification
This thesis presents an LLM-powered active learning framework for cost-effective text classification, addressing the challenge of potential LLM annotation errors while balancing annotation quality and model accuracy. Our methodology combines human and large language model (LLM) annotations using …
-
Adaptive self-prompting in agentic LLM frameworks for embedded code fault detection
… investigates adaptive self-prompting in agentic large language model (LLM) frameworks for code fault detection in embedded systems. Traditional static analysis and existing LLM-based approaches often rely on fixed prompts and exhibit overconfidence, leading to misclassifications. To address these …
-
Trustworthy Intelligence Fusion for Search and Rescue: Designing Grounded and Secure Multi-Agent AI for Mission Decision Support
… information under severe time pressure. Large language model (LLM)-based multi-agent systems (MAS) can support decision-making, but they also risk producing hallucinated outputs and processing unreliable or malicious data. This thesis addresses these risks through three linked studies. …
Page 1 of 13