TSI logo 25 years
LV EN
Home > About Us > Structure and Government > Abstracts

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

Enhancement Strategies for Retrieval-Augmented Generation Systems

This thesis systematically explores the enhancement of Retrieval-Augmented Generation (RAG) systems within Large Language Models, emphasizing optimization of retrieval parameters and generation accuracy. We investigate optimal configurations in RAG systems, including chunk size and overlap percentages, top-k selection, query transformations, different retrieval methods, different LLMs, namely GPT-3.5-Turbo and GPT-4, discovering that a chunk size of 500 tokens generally offers the best performance. Vector search using cosine similarity emerges as the most effective retrieval method, significantly enhancing both context precision and recall across various tasks and knowledge bases. Experimentation within the CRUD-RAG framework demonstrates its applicability in diverse tasks from content creation to knowledge refinement. Our findings indicate that enhancements in retrieval settings can markedly improve the performance of RAG systems, making them more efficient and adaptable for complex information synthesis and retrieval tasks. These results affirm the potential of systematic enhancements to improve AI-driven language models in practical applications, contributing significant insights and practical approaches to the evolving landscape of RAG system research.

Author: Sigita Lapiņa

Supervisor: Dmitry Pavlyuk

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Application of time series algorithms for container imbalance forecasting using event data.

The research aim is to evaluate a time series models application for container imbalance forecasting using container event data. Compare the model results and conclude the real-world application options and limitations. The research object is time series models of container imbalance forecasting and subject is performance of models for container imbalance forecasting based on event data.There are three chapters of the research. The first one is State of the Art on Empty Container Repositioning (ECR) forecasting methods and approaches. The second part is investigation of container imbalance forecasting opportunities using event data. The third part is an application of time-series methods for forecasting container imbalance, experiments with real data and attempts to develop a novel data-driven framework for event data trained time series model evaluation. The third part consists of training experiment results analysis and interpretation. The 8 different models of ARIMA, VAR, VECM algorithms were tested and evaluated by different container size and type combinations, as well of 6 different port locations. Finally, the research conclusions are followed by references and attachments.

Author: Vjačeslavs Matvejevs

Supervisor: Dmitry Pavlyuk

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Apply a Machine Learning Model to Mitigate Bias in the Future AI-based Recruitment

In the contemporary landscape of Human Resources, the integration of artificial intelligence presents both opportunities and challenges, especially in the field of recruitment encompassing all stages of the process, from candidate sourcing to final selection. However, this integration is not without its challenges. Biased data, originating from historical data or societal prejudices, can present a significant obstacle, potentially perpetuating discriminatory practices. The study "Apply a Machine Learning Model to Mitigate Bias in the Future AI-based Recruitment" aims to comprehensively analyze existing biases from both human and artificial intelligence perspectives within the recruitment process. In its framework, answers to the research questions are sought: what are the existing biases in the recruitment process, both explicit and implicit, and how can biases in the recruitment process be effectively mitigated or eliminated through modeling techniques in future AI-based recruitments systems. Through a data-driven approach and the development of machine learning models, will be discover what kind of biases exist in the selection process and how to mitigate them.

Author: Ērika Todjēre

Supervisor: Jeļena Kijonoka

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Table View
Text View