The super alignment of super intelligence with large language models

Speaker: Dr. Minlie Huang
Professor
and
The deputy director of the Foundation Model Center
Tsinghua University

Title: "The super alignment of super intelligence with large language models"

Date: Wednesday, 27 November 2024

Time: 1:30pm - 3:00pm

Venue: Room 4504 (via lift 25/26), HKUST

Abstract: 

With the rapid development of large language models such as GPT-4, Claude, 
and GLM-4, we have witnessed super intelligence, namely human-level or even 
beyond intelligence everywhere. Thus, it becomes more and more critical for 
us to make sure LLMs are really aligned, controllable and safe for our 
societies. In this talk, the speaker will define a key concept - super 
alignment, and talk about the super alignment technologies to the super 
intelligence, including the alignment algorithms, training-free model 
extrapolation, and a conceptual framework for superalignment. He will talk 
about weak-to-strong generalization, scalable oversight, auto red-teaming, 
exact optimization algorithm for alignment, and so on.


**************

Biography:

Dr. Minlie Huang, professor of Tsinghua University, the deputy director of 
the Foundation Model Center of Tsinghua University. He was supported by 
National Distinguished Young Scholar project. He won several awards in 
Chinese AI and information processing societies, including Wuwenjun 
Technical Advancement Award and Qianweichang Technical Innovation Award. His 
research fields include large-scale language models, dialogue systems, and 
language generation. He authored a Chinese book "Modern Natural Language 
Generation". He published more than 150 papers in premier conferences and 
journals (ICML, ICLR, Neurips, ACL, EMNLP etc.), with more than 22,000 
citations, and was selected as Elsevier China's Highly Cited Scholars since 
2022 and the AI 2000 list of the world's most influential AI scholars since 
2020; He has won several best papers or nominations at major international 
conferences (IJCAI, ACL, SIGDIAL, NLPCC, etc.). He led the development of 
several pretrained models including CDial-GPT, EVA, OPD, CPM, CharacterGLM. 
He serves as associate editors for TNNLS, TACL, CL, and TBD, and has served 
as the senior area chair of ACL/EMNLP/IJCAI/AAAI for more than 10 times. His 
homepage is located at .