Dr. Meng Jiang from University of Notre Dame to Give a Research Talk on Large Language Models

Host: Dr. Jian Wu, Assistant Professor of Computer Science, Old Dominion University

Speaker: Dr. Meng Jiang, Associate Professor of Computer Science and Engineering, University of Notre Dame

Location: Engineering and Computational Science Building (ECSB) 1st floor Auditorium

Date and Time: Friday, October 25, 2024 at 10:30 am

Zoom: https://odu.zoom.us/j/94968372478?pwd=FRc3kzcGod3dBOhQbKntcO6DeV5a5S.1

Title: Lessons Learned from Enhancing Knowledge and Reasoning for (Large) Language Models

 

During the past three years (2022-), my students and I have been designing, developing, and evaluating methods to enhance knowledge and reasoning capabilities of language models. In this talk, I’d like to share the lessons we learned from this experience. The talk will answer where the language models can gain knowledge and where they can learn to use the knowledge effectively from, and how. Some interesting questions are: Can large language models (LLMs) verify themselves to answer hard questions? Can LLMs improve themselves by learning from synthetic data? In this talk, if time allows, I will share about an on-going project in our lab on developing educational technologies with LLMs. In the real-world scenarios, we can see great opportunities as well as challenges in AI for Education.

 

Meng Jiang is an associate professor of Computer Science and Engineering at the University of Notre Dame. He received his B.E and Ph.D. from Tsinghua University. Before he joined Notre Dame, he spent a year in CMU, two years as a postdoc in UIUC, and a summer in U Maryland. His research interests are data mining, machine learning, and natural language processing. He has delivered 14 tutorials and organized eight workshops on these topics. He received SIGSOFT distinguished paper award in 2021, NSF CAREER award in 2022, and EMNLP outstanding paper award in 2023.