Sponsored jointly by the School of Computer Science and Engineering and the College of Information Sciences and Technology, join Heng Ji for her research talk, "Making Large Language Model’s Knowledge More Accurate, Organized, Up-to-date and Fair." This talk is free and open to the public.
"Making Large Language Model’s Knowledge More Accurate, Organized, Up-to-date and Fair"
About This Talk: Large language models (LLMs) have demonstrated remarkable performance on knowledge reasoning tasks, owing to their implicit knowledge derived from extensive pretraining data. However, their inherent knowledge bases often suffer from disorganization and illusion, bias towards common entities, and rapid obsolescence. In this talk I will aim to answer the following questions: (1) Where and How is Knowledge Stored in LLM? (2) Why does LLM Lie? (3) How to Update LLM’s Dynamic Knowledge? (4) How to Reach LLM’s Knowledge Updating Ripple Effect? and (5) What can knowledge + LLM do for us? I will present a case study on “SmartBook” – situation report generation.
About the Speaker: Heng Ji is a professor in the Computer Science Department, and an affiliated faculty of the Electrical & Computer Engineering Department and Coordinated Science Laboratory of Univ. of IL, Urbana-Champaign. She is an Amazon Scholar, and Founding Director of Amazon-Illinois Center on AI for Interactive Conversational Experiences (AICE). Her awards include Outstanding Paper Award at ACL2024, two Outstanding Paper Awards at NAACL2024, “Young Scientist” by the World Laureates Association in 2023 and 2024.