Title
Some thinking about LLM reasoning ability
Abstract
The generative artificial intelligence (GAI) and the large language model (LLM) emerged in recent decade are leading to a revolution of AI in academic world and industrial circle. Since Chat GPT-4, LLMs begin to develop quickly and, with respect to many specific tasks, LLMs have the emergent phenomena. However, with the many LLM applications, several critical problems are disclosed such as uncertain answers to the same query, critical mistakes for simple queries, and little ability of human-like reasoning. Focusing on the problem whether or not LLMs have the reasoning ability of human-like, this talk shares some study notes of the speaker and some personal thinking.
Biographies
Xizhao Wang received his PhD from Harbin Institute of Technology in 1998. He is currently a professor at college of computer science in Shenzhen University. Previously he was the dean of computer science college in Hebei university from 2000 to 2014.
Prof. Wang's current research interests include uncertainty-aware machine learning and lightweight of large language model. He pioneered the research on Machine Learning in uncertain environment, and published several monographs and textbooks, and over 300 research papers at conferences and in journals. His works have been cited 14,178 times according to Google scholar in 2023. He was on the list of Highly Cited Researchers by Clarivate in 2019 and 2020, in recognition of exceptional research performance demonstrated by production of multiple highly cited papers that rank in the cross-field top 1%.
Prof. Wang is an IEEE Fellow (2012), a CAAI Fellow (2017), and the Editor-in-Chief of Springer Journal Machine Learning and Cybernetics (from 2010 to present).
