College of Computing and Digital Media Dissertations

Date of Award

Summer 8-22-2024

Degree Type

Thesis

Degree Name

Master of Science (MS)

School

School of Computing

First Advisor

Noriko Tomuro, PhD

Second Advisor

Vahid Alizadeh, PhD

Third Advisor

Jamshid Sourati, PhD

Abstract

Large Language Models (LLMs) have shown exceptional performance in several natural language processing (NLP) tasks. Customizing LLMs boosts their performance in domain specific tasks but typically requires substantial resources and effort for training, such as supervised fine-tuning. This research proposes methods to achieve significant accuracy improvements given minimal resources, particularly focusing on open-ended question answering with a given piece of context. We utilize an LLM’s self-generated training data to fine-tune the LLM and partial fine-tuning with on-demand GPU to reduce practitioner training costs. The research shows that these methods give significant performance gains in a Retrieval Augmented Generation (RAG) based system on the Stanford Question Answering Dataset (SQuAD).

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.