AI & Fundamentals

LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language - James Requeima, Postdoctoral Fellow, University of Toronto

Abstract:

Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses. Moreover, the expertise needed to integrate this prior knowledge into probabilistic modeling typically limits the application of these models to specialists. In this talk, we present a regression model that can process numerical data and make probabilistic predictions at arbitrary locations, guided by natural language text which describes a user's prior knowledge. Large Language Models (LLMs) provide a useful starting point for designing such a tool since they 1) provide an interface where users can incorporate expert insights in natural language and 2) provide an opportunity for leveraging latent problem-relevant knowledge encoded in LLMs that users may not have themselves. We start by exploring strategies for eliciting explicit, coherent numerical predictive distributions from LLMs. We examine these joint predictive distributions, which we call LLM Processes and we demonstrate the ability to usefully incorporate text into numerical predictions, improving predictive performance and giving quantitative structure that reflects qualitative descriptions. This lets us begin to explore the rich, grounded hypothesis space that LLMs implicitly encode.

Bio:

James Requeima is currently a postdoctoral fellow at the University of Toronto and the Vector Institute in Toronto, Canada. His supervisor is David Duvenaud. He's interested in meta-learning, neural processes, deep probabilistic models and using LLMs for probabilistic regression. His PhD was in machine learning at the University of Cambridge in the Computational and Biological Learning Lab. His advisor was Dr. Richard Turner. He was recently a visiting student at MILA under the supervision of Yoshua Bengio. Previously, he completed a Master's in machine learning, speech and language technology at the University of Cambridge where his advisor was Dr. Zoubin Ghahramani FRS. More info about James at jamesr.info.