Sökning: "Prompt Engineering"

Visar resultat 1 - 5 av 30 uppsatser innehållade orden Prompt Engineering.

  1. 1. An In-Depth study on the Utilization of Large Language Models for Test Case Generation

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Nicole Johnsson; [2024]
    Nyckelord :Large Language Models; Test Case Generation; Retrieval Augmented Generation; Machine Learning; Generative AI;

    Sammanfattning : This study investigates the utilization of Large Language Models for Test Case Generation. The study uses the Large Language model and Embedding model provided by Llama, specifically Llama2 of size 7B, to generate test cases given a defined input. LÄS MER

  3. 2. Framtidens copywriter är AI - eller? : En experimentell studie som undersöker relationen mellan generativ artificiell intelligens och copywritingkompetensen inom kommunikatörsprofessionen

    Kandidat-uppsats, Karlstads universitet/Institutionen för geografi, medier och kommunikation (from 2013)

    Författare :Amelia Andersson; Åsa Engström; [2024]
    Nyckelord :Generative Artificial Intelligence; copywriting; credibility; conviction; Generativ artificiell intelligens; copywriting; trovärdighet; övertygelse;

    Sammanfattning : The purpose of the study was to examine whether it was possible to discern any effect on the perception of the content of a copytext in terms of credibility and conviction, depending on whether the writer was ChatGPT or a human copywriter, and whether it was possible to discern any effect on the perception of the writer in terms of creativity and professionalism. To achieve the purpose of the study, the following questions were formulated: 1. LÄS MER

  4. 3. Bridging Language & Data : Optimizing Text-to-SQL Generation in Large Language Models

    Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

    Författare :Niklas Wretblad; Fredrik Gordh Riseby; [2024]
    Nyckelord :Chaining; Classification; Data Quality; Few-Shot Learning; Large Language Model; Machine Learning; Noise; Prompt; Prompt Engineering; SQL; Structured Query Language; Text-to-SQL; Zero-Shot Learning; Noise Identification;

    Sammanfattning : This thesis explores text-to-SQL generation using Large Language Models within a financial context, aiming to assess the efficacy of current benchmarks and techniques. The central investigation revolves around the accuracy of the BIRD-Bench benchmark and the applicability of text-to-SQL models in real-world scenarios. LÄS MER

  5. 4. Prompt engineering guidelines for LLMs in Requirements Engineering

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Simon Arvidsson; Johan Axell; [2023-08-07]
    Nyckelord :Requirements Engineering; Prompt Engineering; Generative AI; LLM; Prompt Guidelines;

    Sammanfattning : The rapid emergence of large generative AI models has demonstrated their utility across a multitude of tasks. Ensuring the quality and accuracy of the models’ output is done in different ways. In this study, we focused on prompt engineering. LÄS MER

  7. 5. Exploring the Efficacy of ChatGPT in Generating Requirements: An Experimental Study

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Leila Bencheikh; Niklas Höglund; [2023-08-03]
    Nyckelord :ChatGPT; AI-detector accuracy; requirements; experimental study;

    Sammanfattning : This thesis explores the efficacy of ChatGPT in generating software requirements and compares its performance to human participants through an experimental study. The study addresses three main research questions (RQs), examining how ChatGPT-generated requirements align with human-written requirements, the variation in quality between different versions of ChatGPT using two additional sub-questions that look at improvement in quality from feedback and consistency of quality when the same prompt is queried multiple times, and the capacity of the Content at Scale AI detector in identifying AI-generated requirements. LÄS MER