In recent years, large language models (LLMs) have emerged as transformative tools in the realm of artificial intelligence. They show strong language understanding and reasoning capabilities, presenting a wealth of opportunities for solving challenging problems. However, deploying them as independent problem solvers - even with sophisticated prompting techniques - often ends up with unsatisfactory results. In this talk, I will introduce an alternative approach, which incorporates LLMs within a larger framework for complex reasoning. Here, LLMs propose solutions or logical pathways, which are then analyzed and utilized by the framework. We will showcase two challenging problems effectively addressed using this paradigm. The first is text-based logical reasoning, in which one has to determine the truth value of a statement given a set of rules and facts, expressed in human natural language. The second is event prediction, the task of reasoning about future events given the past. For both problems, our LLM-as-Lego-blocks frameworks learn to provide high-quality output beyond what an LLM can offer as a standalone problem solver. I will sketch a few future research directions for improving the fundamental reasoning capabilities of LLMs.
Dr. Hongyuan Mei is currently a Research Assistant Professor at Toyota Technological Institute at Chicago (TTIC). He obtained his PhD from the Department of Computer Science at Johns Hopkins University (JHU), where he was advised by Jason Eisner. Hongyuan's research spans machine learning and natural language processing. Currently, he is most interested in harnessing and improving the reasoning capabilities of large language models to solve challenging problems such as event prediction. His research has been supported by a Bloomberg Data Science PhD Fellowship, the 2020 JHU Jelinek Memorial Award, and research gifts from Adobe and Ant Group. His technical innovations have been integrated into real-world products such as Alipay, the world’s largest mobile digital payment platform, which serves more than one billion users. His research has been covered by Fortune Magazine and Tech At Bloomberg.