Grant: Discovery Grants Program - Individual

We, humans, are very good at decision-making. When building automated methods for decision-making, computer scientists, including mathematicians and engineers in artificial intelligence, take inspiration from humans. In particular, we are trying to build computer systems that reach human-level performance. If such methods were successful, they could assist humans in making even better decisions. This could be particularly useful in situations where we are faced with many choices or situations where we do not know about the possible outcomes of each choice. Examples include critical decisions about treatment options for a particular medical condition or, more mundane ones, like choosing the next book to read from a large catalogue of books or a group of stocks to add to our financial portfolio. One approach in artificial intelligence research is to frame such problems as a recommender system. At their core, recommender systems find patterns in user behaviour to improve personalized experiences and understand the environment, or the context, that they are acting in. The simplest recommender system suggests items of interest to its users based on their past behaviour (for example the next book to read or person to date). While recommender systems are an important field of current research and are widely deployed (think of social media feeds, Google's search suggestions or Amazon's "Customers Who Bought This Item Also Bought") their capabilities are limited. Of crucial importance to these systems is the ability to understand the nuances of user preferences and the context surrounding a decision. To obtain and model finer-grain data, recommender systems must be "in the loop" and be able to interact more freely with their users.   This research project will design novel mathematical tools using machine learning methods for recommender systems. Specifically, my research will develop and validate techniques associated with large-language models. Such models show impressive language modelling capabilities. Combining them with recommender systems can yield systems that can better interact with their users, systems whose decisions (recommendations) are easier to interpret, control, and ultimately safer. This research will contribute to Canada's position as a leader in artificial intelligence and fuel downstream applications, such as automated health assistants, that can help Canadians in their daily lives.