Keynote 5: Large Language Models for NLP applications and beyond

    by Prof. Nguyen Le Minh, Japan Advanced Institute of Science and Technology (JAIST).


    Large language model families, including ChatGPT, demonstrate very high performance and have made significant breakthroughs in real-world applications. In this talk, we would like to highlight the core technology used to build large language models and discuss the growing trend of utilizing these models in various NLP applications. Furthermore, we will delve into the potential issues associated with using such models, focusing on topics like bias, security, and privacy. In the final part of my talk, we will showcase our current deep learning-based techniques for analyzing legal documents. Additionally, we will discuss our system's exceptional performance in the Competition on Legal Information Extraction/Entailment, where we achieved outstanding results.


    Minh Le Nguyen received a B.Sc. degree in computer science from Hanoi National University, Hanoi, Vietnam, in 1998, a master’s degree from the College of Technology, Vietnam National University, Hanoi, in 2001, and a Ph.D. degree in information science from the Graduate School of Information Science, JAIST, Ishikawa, Japan, in 2004. He is currently working as a Professor with the Graduate School of Information Science, JAIST. He is also a director of the Interpretable AI Center at JAIST. His research interests include machine learning, deep learning, text summarization, machine translation, natural language understanding, legal engineering, and grammatical analysis of music. He serves as an Editorial Board member of Artificial Intelligence and Law and TACL - Transactions of the Association for Computational Linguistics. He is a steering committee member of JURISIN in Japan, and he is also the general chair of the KSE conference series