Abstract: 

The rapidly evolving realm of large language models (LLMs) presents novel opportunities for causal analysis. In our groundbreaking workshop, participants will embark on a journey to harness the untapped potential of LLMs for sourcing both common and expert causal knowledge. Beginning with the fundamentals, we will delve deep into the methodologies of extracting and interpreting causal knowledge from LLMs, and how to the LLMs to cast that knowledge into causal models and utilize them for comprehensive causal analysis. A highlight of this workshop is the introduction to the "causal LLM", a pioneering concept where LLMs are designed using foundational causal principles. By the end of this session, participants will be equipped with the skills and knowledge to employ LLMs effectively in discerning complex causal models and pioneering advancements in the field of causal AI.

Session Outline:

By the end of this session, participants will be equipped with the skills and knowledge to employ LLMs effectively in discerning complex causal models and pioneering advancements in the field of causal AI.

Background Knowledge:

Some basic knowledge of causal inference and analysis.

Bio: 

Robert Osazuwa Ness is a researcher at Microsoft Research and author of the book Causal Machine Learning. He leads the development of MSR’s causal machine learning platform and conducts research into probabilistic models for advanced causal reasoning. He has worked as a machine learning engineer in various machine learning startups. He attended graduate school at both Johns Hopkins SAIS (Hopkins-Nanjing Center) and Purdue University. He received his Ph.D. in Statistics from Purdue, where his dissertation research focused on Bayesian active learning models for causal discovery.