FINTECH THRUST SEMINAR | Towards Reliable Large Language Model Systems
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
Towards Reliable Large Language Model Systems
Abstract:
Large Language Models (LLMs) have become a cornerstone of modern artificial intelligence, offering unprecedented capabilities in natural language processing and generation. Their dependability, however, is a multifaceted concept that encompasses reliability, security, and privacy. Various recent studies have illustrated rather low reliability or unsafety in LLM systems, illustrating concerns that jeopardize real-world usage of LLMs. In this talk, Shuai will introduce their several recent works on assessing and enhancing LLM reliability from the model, software, and system perspectives. He will also discuss some promising future directions that facilitate building reliable LLM-integrated systems.
Shuai Wang is an Associate Professor at the Department of Computer Science and Engineering (CSE), the Hong Kong University of Science and Technology (HKUST). He is broadly interested in computer security and privacy, with a particular focus on AI reliability, AI security, and data privacy. He received the Early Career Award from the Hong Kong RGC in 2020, several industrial research awards from Google/Alibaba DAMO Academy/Tencent, as well as several best paper awards in top conferences such as IEEE S&P 2025 and ASE 2023.