Sökning: "retrieval models"
Visar resultat 1 - 5 av 100 uppsatser innehållade orden retrieval models.
1. An In-Depth study on the Utilization of Large Language Models for Test Case Generation
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : 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
2. Exploring Attachment Dynamics: Implications for Overgeneralized Memory and Rumination
Master-uppsats, Lunds universitet/Institutionen för psykologiSammanfattning : Objective and Methods: This thesis investigates the relationship between insecure attachment (anxiety and avoidance), rumination, and overgeneralized episodic memory retrieval in nonclinical adults, addressing the potential moderating role of rumination in the attachment- overgeneralization link. A community sample of 41 Swedish-speaking women participated in a narrative memory task involving attachment and non-attachment narratives. LÄS MER
3. Leveraging Large Language Models for Firm-Intelligence: A RAG Framework Approach
Magister-uppsats, Lunds universitet/Statistiska institutionenSammanfattning : In the wake of OpenAI's release of ChatGPT in November 2022, powered by the 175 billion parameter neural network GPT-3, the potential applications of Large Language Models (LLMs) in various sectors have become evident. One such application lies in hedge funds and trading desks where knowledge sharing is paramount. LÄS MER
4. Generating an Interpretable Ranking Model: Exploring the Power of Local Model-Agnostic Interpretability for Ranking Analysis
Magister-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Machine learning has revolutionized recommendation systems by employing ranking models for personalized item suggestions. However, the complexity of learning-to-rank (LTR) models poses challenges in understanding the underlying reasons contributing to the ranking outcomes. LÄS MER
5. Learning Embeddings for Fashion Images
Master-uppsats, Linköpings universitet/DatorseendeSammanfattning : Today the process of sorting second-hand clothes and textiles is mostly manual. In this master’s thesis, methods for automating this process as well as improving the manual sorting process have been investigated. LÄS MER