On the capabilities and risks of large language models

Huang, Jie

Permalink

https://hdl.handle.net/2142/125556 Copy

Description

Title

On the capabilities and risks of large language models

Author(s)

Huang, Jie

Issue Date

2024-07-03

Director of Research (if dissertation) or Advisor (if thesis)

Chang, Kevin Chen-Chuan

Doctoral Committee Chair(s)

Chang, Kevin Chen-Chuan

Committee Member(s)

• Peng, Hao
• Tong, Hanghang
• Xu, Tianyin
• Yang, Diyi

Department of Study

Siebel Computing &DataScience

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• large language model
• reasoning
• privacy
• ethics

Abstract

The advent of Large Language Models (LLMs) has significantly influenced the field of artificial intelligence, offering remarkable text generation capabilities through their vast number of parameters. These advancements have established new benchmarks across various domains. However, despite the impressive capabilities of LLMs, there exist critical limitations and ethical challenges. This dissertation critically examines the capabilities of LLMs, including their reasoning abilities, and explores potential risks, such as privacy leakage. Through this analysis, we underscore the crucial need to improve the capabilities of LLMs while mitigating the associated risks. Based on this understanding, we propose methodologies to augment and safeguard LLMs. To enhance their functionality, we develop techniques to integrate LLMs with external knowledge and design an innovative data structure for knowledge representation. Additionally, we advocate for incorporating citation mechanisms within LLMs to promote transparency, accountability, and respect for intellectual property. Through rigorous research and the introduction of cutting-edge techniques, this dissertation aims to advance the capabilities of LLMs while ensuring their responsible and ethical use, ultimately contributing to the development of powerful and trustworthy artificial intelligence systems.

Graduation Semester

2024-08

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/125556

Copyright and License Information

Copyright 2024 Jie Huang

Owning Collections