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 2381 for “"LLM"”.
-
Programavimas naudojant LLM /
This thesis investigates whether a multiagent LLM architecture produces higher-quality code than a single-agent architecture when solving complex, well-specified programming tasks, and whether this difference scales with task difficulty. For the investigation, a custom system was implemented using …
-
LLM meta-materials : a paradigm shift in architecture through LLM-driven synthetic materials
… the potential of Large-Language Models (LLMs) in advancing material discovery for architectural applications, proposing a replicable workflow for developing alternatives to traditional construction materials. This thesis seeks to answer the possibility of predicting the synthesis process …
-
Texas Hold’em poker by LLM
This report introduces a novel approach for utilizing a large language model, LLAMA2 Touvron et al. (2023), to analyze and solve Texas Hold’em poker. By leveraging in-context learning Brown et al. (2020), and policy iteration Sutton and Barto (1998), we develop a method that can iteratively learn …
-
ResearchBuddy AI: LLM-Powered Assistant
This paper presents ResearchBuddy AI, an LLM-powered assistant that addresses modern research information overload problems. The project has three essential features, including finetuning of large language models for structured research paper summarization, prompt engineering for flexible …
-
Dataset Augmentation for LLM Reasoning
Fine-tuning large language models (LLMs) typically requires a large number of input-output x, y pairs. In common fine-tuning practices, a model learns from input-output pairs provided by a dataset. However, for many tasks—particularly reasoning tasks—there can be multiple valid ways to express …
-
Programinio kodo generavimas naudojant LLM /
Recently, there has been an increasing focus on the continuous development and creation of large language models, which are fundamentally changing our daily lives. One of the most common areas where this technology is widely used is in the generation of software code. However, to make good use of …
-
Exploring Patterns in LLM Integration
… in the integration of Large Language Models (LLMs) into software applications marks an evolution in the software development industry, leading to research into architectural frameworks and design patterns suitable for these technologies. This study aims to analyze the implementation of LLMs in …
-
Sémantická analýza logů pomocí LLM
… se zabývá využitím velkých jazykových modelů (LLM) pro automatizaci sémantické analýzy logovacích záznamů, konkrétně pro anotaci dynamických parametrů v logových šablonách. Vzhledem k rostoucímu objemu logových dat a potřebě hlubšího porozumění jejich obsahu práce zkoumá potenciál LLM pro tuto …
-
Interactive Evaluation of LLM-based Agents
… chatbot development. From rule-based chatbots to LLM-based chatbots, evaluating the effectiveness of personality design has become more challenging due to the increasingly open-ended interactions. A recent popular approach uses self-report questionnaires to assess LLM-based chatbots' personality …
-
Structural Insights for LLM Serving Efficiency
The widespread adoption of Large Language Models (LLMs) has reshaped the datacenter computing landscape. As these models continue to grow in size and complexity, they require increasingly expensive and power-intensive infrastructure. Hence, serving LLMs efficiently has become critical for managing …
-
LLM naudojimas interaktyvioms audio knygoms kurti /
… examines the use of large language models (LLMs) for the creation of interactive and personalized audiobooks. The aim of the thesis is to develop a prototype interactive audiobook system that generates a narrative in real time based on user preferences and to evaluate the impact of …
-
Prompt enrichment for Geospatial LLM inference
… συμπερασμάτων από Μεγάλα Γλωσσικά Μοντέλα (LLM) για εργασίες με χωρική επίγνωση. Η παρούσα διατριβή αναπτύσσεται ως βελτίωση του πειράματος της δημοσίευσης του Manvi [12] που αξιοποιεί τα LLMs για εξαγωγή συμπερασμάτων σε γεωχωρικά δεδομένα με τη χρήση prompts προσαρμοσμένων για αυτό το …
-
Generování strukturovaných testovacích dat pomocí LLM
Cílem této bakalářské práce je vyvinout nástroj schopný rozšiřovat existující testovací sady ve formátu JSON o automaticky generované platné i neplatné testovací příklady. Proces generování využívá kombinovaný přístup: zatímco velké jazykové modely se využívají k syntéze složitých datových hodnot, …
-
Generování strukturovaných testovacích dat pomocí LLM
… s pomocou lokálneho veľkého jazykového modelu (LLM) cez platformu Ollama vygeneruje recept. Samotné generovanie je rozložené do štyroch fáz, ktoré sú doplnené o validačnú a opravnú vrstvu. Vyhodnotenie úspešnosti je vykonané na troch úrovniach, pri modeli qwen2.5 na sade 31 testovacích databáz …
-
Rethinking Code ReviewWorkflows with LLM Assistance
… field experiment involving two variations of an LLM-assisted code review tool. The field study identifies key challenges in traditional code reviews, including frequent context switching, insufficient contextual information, and highlights both opportunities (e.g., automatic summarization of …
-
Digital Peer-Reviewer with LLM-integration
This project develops an AI-powered web application to automate academic peer review processes and assess research novelty. Built on the MERN stack, the system integrates DeepSeek’s language model to generate structured reviews and utilizes PubMed’s database to identify similar research through …
-
Vyhodnocování kvality požadavků pomocí LLM modelů
… který ukazuje, jak může zpětná vazba založená na LLM podporovat inženýry požadavků při kontrole a~zpřesňování požadavků.
-
Využití auto-promptingu pro optimalizaci LLM
Táto práca sa zaoberá využitím auto-promptingu na optimalizáciu výstupov veľkých jazy- kových modelov bez potreby ich ďalšieho trénovania. Cieľom bolo navrhnúť, implementovať a otestovať modul, ktorý automaticky zlepšuje prompty používané v systéme Lakmoos AI. Modul bol zameraný hlavne na …
-
Evaluation of LLM-driven Data Preparation
Large language models (LLMs) have increasingly been used in data preparation pipelines due to their strong natural language understanding and reasoning capabilities. Data preparation tasks such as entity matching, and missing value imputation often rely on identifying syntactic patterns in the …
-
SECURITY ENHANCEMENTS FOR LLM-BASED CHATBOTS
Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2025
Page 1 of 120