2026-09-20T00:21:32Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/125556 2025-02-06 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms The student, Jie Huang, accepted the attached license on 2024-07-02 at 11:17. The student, Jie Huang, submitted this Dissertation for approval on 2024-07-02 at 11:40. This Dissertation was approved for publication on 2024-07-03 at 09:03. DSpace SAF Submission Ingestion Package generated from Vireo submission #20915 on 2025-02-04 at 21:04:04 Chang, Kevin Chen-Chuan Peng, Hao Tong, Hanghang Xu, Tianyin Yang, Diyi Large Language Model Reasoning Privacy Ethics eng 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. 2024-08 Thesis https://hdl.handle.net/2142/125556 Copyright 2024 Jie Huang On the capabilities and risks of large language models Huang, Jie 2024-07-03 Chang, Kevin Chen-Chuan Siebel Computing &DataScience Computer Science University of Illinois at Urbana-Champaign Ph.D. Dissertation