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 111 for “"GPT 4"”.

  1. Classifying Code as Human Authored or GPT-4 Generated

    … (AI) assistants such as GitHub Copilot and ChatGPT, built on large language models like GPT-4, are revolutionizing how programming tasks are performed, raising questions about whether generative AI models author code. Such questions are of particular interest to educators, who worry that these …

    waterloo Repository record for Classifying Code as Human Authored or GPT-4 Generated (opens in a new tab)

  2. Detection of Counterfeit Coins Using Multimodal GPT-4 and Vision Transformer

    … Vision Transformer (ViT) model and a multimodal GPT-4 model. The ViT model leverages its self-attention mechanisms to capture intricate patterns and details within the coin images, while the GPT-4 model integrates both visual and textual data, utilizing various prompting techniques to enhance its …

    concordia Download PDF for Detection of Counterfeit Coins Using Multimodal GPT-4 and Vision Transformer (opens in a new tab)

  3. Automating Protocol Analysis with Generative AI: Classifying Questions in Design Review Meetings Using GPT-4

    … was conducted to evaluate the performance of GPT-4, a state-of-the-art generative AI model, in this context. The experiments involved utilizing ICL by providing the AI model on a dataset of human-labeled questions and testing its ability to classify new questions according to predefined …

    waterloo Repository record for Automating Protocol Analysis with Generative AI: Classifying Questions in Design Review Meetings Using GPT-4 (opens in a new tab)

  4. Asistente virtual holográfico para el apoyo de escolares de 8 a 12 años potenciado con GPT-4

    … animado interactivo, impulsado por la tecnología GPT-4, que actúa como asistente educativo. Este avatar será proyectado como un holograma a través de una pirámide holográfica, ofreciendo respuestas orales y facilitando una experiencia educativa inmersiva. El objetivo principal del proyecto es …

    upc-peru Repository record for Asistente virtual holográfico para el apoyo de escolares de 8 a 12 años potenciado con GPT-4 (opens in a new tab)

  5. Chatbot basado en GPT 4 para la atención a reclamos de soporte técnico en una empresa de telecomunicaciones

    … se implementó un chatbot basado en la tecnología GPT-4, con el objetivo de asistir al área de soporte técnico. El chatbot fue entrenado con información específica sobre los procedimientos internos de la empresa y configurado para resolver consultas frecuentes, brindar orientación en soluciones …

    upc-peru Repository record for Chatbot basado en GPT 4 para la atención a reclamos de soporte técnico en una empresa de telecomunicaciones (opens in a new tab) Restricted access

  6. Aplicación web de encuestas de pulso personalizadas para la evaluación del clima organizacional dirigida a PYMEs utilizando GPT-4

    … personalizadas. Utilizando la tecnología de GPT-4, la aplicación facilita la recolección y clasificación continua de datos, adaptándose constantemente a las necesidades específicas de cada empresa a medida que se recopilan y analizan más resultados. Al ser desplegada en un entorno de Azure …

    upc-peru Repository record for Aplicación web de encuestas de pulso personalizadas para la evaluación del clima organizacional dirigida a PYMEs utilizando GPT-4 (opens in a new tab)

  7. Examining the Effectiveness of Generative Artificial Intelligence for the Identification of Defeaters in Assurance Cases

    … this process, we explore the capabilities of GPT-4 Turbo, a sophisticated large language model by OpenAI. We focus on its application in detecting defeaters within assurance cases represented using Eliminative Argumentation(EA) notation. Our initial evaluation assesses GPT-4 Turbo’s …

    york Repository record for Examining the Effectiveness of Generative Artificial Intelligence for the Identification of Defeaters in Assurance Cases (opens in a new tab)

  8. Sistema web basado en LLM para optimizar la gestión de reclamos en el sector de telecomunicaciones

    … de lenguaje grande (LLM), específicamente GPT-4, para optimizar la gestión de reclamos en una empresa del sector telecomunicaciones. El problema central identificado es la demora significativa en la atención de reclamos, ocasionada por procesos manuales, sobrecarga operativa y falta de …

    upc-peru Repository record for Sistema web basado en LLM para optimizar la gestión de reclamos en el sector de telecomunicaciones (opens in a new tab)

  9. Design and Automatic Generation of Safety Cases of ML-Enabled Autonomous Driving Systems

    … Finally, leveraging large language models like GPT-4, we conducted experiments to automate safety case generation. Results indicate that GPT-4 produces safety cases with moderate accuracy and high semantic similarity to ground truth cases. This comprehensive methodology enhances safety …

    york Repository record for Design and Automatic Generation of Safety Cases of ML-Enabled Autonomous Driving Systems (opens in a new tab)

  10. Automated goal model generation from user stories using Large Language Models

    … with tools like jUCMNav. The study evaluates GPT-4, Llama, and Cohere, focusing on syntactic completeness and correctness. GPT-4 outperforms others, particularly in extracting implicit goals and soft goals, but struggles with intricate relationships like means-end and contribution links. …

    uoit Repository record for Automated goal model generation from user stories using Large Language Models (opens in a new tab)

  11. Enhancing fact-checking in large language models: Cost-effective claim verification through first-order logic reformulation

    … benchmarking of various LLMs, including GPT-4, on this critical task. We utilize a modern, challenging dataset designed explicitly for fact-checking, HOVER, which comprises thousands of evidence-claim pairs covering diverse aspects of life, history, and entertainment. This dataset differs …

    uvic Repository record for Enhancing fact-checking in large language models: Cost-effective claim verification through first-order logic reformulation (opens in a new tab)

  12. Comparing the persuasiveness of humans and large language models in persona-based dialogue

    … a human persuader or an LLM persuader based on GPT-4. We find that, in this setting, GPT-4 is perceived as both more persuasive and more empathetic, whereas humans are more skilled at discovering new information about the person they are speaking to. This research provides the groundwork for …

    ubc Repository record for Comparing the persuasiveness of humans and large language models in persona-based dialogue (opens in a new tab) Download PDF for Comparing the persuasiveness of humans and large language models in persona-based dialogue (opens in a new tab)

  13. AI-Driven Digital Twin for Visual Defect Inspection in Railway Prognostics and Health Management

    … achieved a precision of 0.92, outperforming GPT-4 at 0.68 and Gemini-Pro-Vision at 0.88, with an F1-score of 0.92. In zero-shot scenarios, DefectTwin achieved a precision of 0.60 compared to GPT-4 at 0.40 and Gemini-Pro-Vision at 0.48, with an F1-score of 0.62. For video data, zero-shot …

    ottawa-retro Repository record for AI-Driven Digital Twin for Visual Defect Inspection in Railway Prognostics and Health Management (opens in a new tab)

  14. USE OF LARGE LANGUAGE AND REASONING MODELS IN THE GENERATION AND EVALUATION OF EXPERT- AND PATIENT-ORIENTED SUMMARIES OF RADIOLOGY REPORT FINDINGS

    … thesis paper were to (1) evaluate five LLMs [GPT-4, GPT-4o mini, Gemini 1.5 – Pro, Gemini 1.5 – Flash, and Llama 3.1] for impression generation (expert-facing) and (2) lay summaries (patient-facing), (i) using a mixed-method evaluation framework compare laypersons and a Large Reasoning Model …

    mcmaster Repository record for USE OF LARGE LANGUAGE AND REASONING MODELS IN THE GENERATION AND EVALUATION OF EXPERT- AND PATIENT-ORIENTED SUMMARIES OF RADIOLOGY REPORT FINDINGS (opens in a new tab)

  15. Natūralios kalbos transliavimo į predikatų logikos kalbą galimybės, naudojant didžiuosius kalbos modelius /

    … effort required, while commercial models such as GPT-4, despite achieving high syntactic accuracy, raise concerns regarding data privacy and economic accessibility. The thesis reviews the existing literature on commercial GPT models and the specialized LogicLLaMA solution. The practical …

    vilnius Repository record for Natūralios kalbos transliavimo į predikatų logikos kalbą galimybės, naudojant didžiuosius kalbos modelius / (opens in a new tab)

  16. Simulace procházení webu člověkem

    … z dané stránky. Výsledky simulátoru s modelem GPT 4 Turbo demonstrují efektivitu tohoto nástroje, který dosahuje úspěšnosti přes 80% v dokončování předem definovaných cílů. Výsledky dokazují použiteljnost tohoto nástroje v reálných případech užití.

    brno-tech Repository record for Simulace procházení webu člověkem (opens in a new tab)

  17. Improving Foundation Models

    Foundation models are the family of models (e.g. GPT-4, CLIP) that are trained on a massive dataset and perform various down-streaming tasks, usually with either zero- or few-shot learning, optionally after fine-tuning. This dissertation presents a wide range of important measures we have made to …

    gatech Repository record for Improving Foundation Models (opens in a new tab)

  18. Snjallar starfsáætlanir

    … notendavænu vefviðmóti, bakenda og tengingu við GPT-4 í gegnum Azure OpenAI. Í ritgerðinni er farið ítarlega yfir hönnun, þróun, þarfagreiningu, prófanir og framvindu verkefnisins, ásamt áhættugreiningu og framtíðarsýn.

    reykjavik Repository record for Snjallar starfsáætlanir (opens in a new tab)

  19. Towards Personalized LLMs: Investigating Narrative Generation and Personality-Based Preferences in Large Language Models

    … Keirsey personality types, users engaged with GPT-4 and Claude 3.5 across four collaborative tasks: data analysis, creative writing, information retrieval, and writing assistance. Findings reveal personality-based preferences: Rationals favored GPT-4 for goal-oriented tasks, while Idealists …

    brock Repository record for Towards Personalized LLMs: Investigating Narrative Generation and Personality-Based Preferences in Large Language Models (opens in a new tab)

Page 1 of 6