News
The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.
On November 28, Dr. Hongyuan Mei —Research Assistant Professor at Toyota Technological Institute at Chicago — presented “Language Models as Lego Blocks of Reasoning" at the AI Seminar.
Abstract:
In recent years, language models (LMs) 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, Mei introduces an alternative approach, which incorporates LMs within a larger framework for complex reasoning. Here, LMs propose solutions or logical pathways, which are then analyzed and utilized by the framework. They 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, the LM-in-the-loop frameworks learn to provide high-quality output beyond what an LM can offer as a standalone problem solver.
Mei sketches a few future research directions for improving the fundamental reasoning capabilities of LMs, including embedding an LM within a reinforcement learning framework to develop foundation world models.
Watch the full presentation below:
Want to learn how you can kick-start your AI career? Find out more about Amii's Career Accelerator to find out more.
May 16th 2024
News
Amii and New Harvest are excited to announce phase two of their research collaboration focused on applications of artificial intelligence and machine learning in cellular agriculture. The new phase initiates a year-long project with an open call to researchers and experts specializing in cellular agriculture and machine learning who want to apply ML solutions to solve the challenges in the field.
May 7th 2024
News
Check out the advancements being presented by Amii researchers at the 2024 International Conference on Learning Representation.
May 2nd 2024
News
Read our monthly update on Alberta’s growing machine intelligence ecosystem and exciting opportunities to get involved.
Looking to build AI capacity? Need a speaker at your event?