AI Trends 2023: Causality and the Impact on Large Language Models with Robert Ness
EPISODE 616
|
FEBRUARY
14,
2023
Watch
Follow
Share
About this Episode
Today we’re joined by Robert Osazuwa Ness, a senior researcher at Microsoft Research, to break down the latest trends in the world of causal modeling. In our conversation with Robert, we explore advances in areas like causal discovery, causal representation learning, and causal judgements. We also discuss the impact causality could have on large language models, especially in some of the recent use cases we’ve seen like Bing Search and ChatGPT. Finally, we discuss the benchmarks for causal modeling, the top causality use cases, and the most exciting opportunities in the field.
About the Guest
Robert Ness
Microsoft Research, Northeastern University
Connect with Robert
Resources
- Check out Robert's new book, Causal Machine Learning!
- Causal AI Book
- On the Generalization and Adaption Performance of Causal Models
- Learning neural causal models from unknown interventions
- Learning to induce causal structure
- Amortized inference for causal structure learning
- ClimaX: A foundation model for weather and climate
- Inducing causal structure for interpretable neural networks
- Desiderata for representation learning: A causal perspective
- Weakly supervised causal representation learning
- Distilling problems and benchmarks to core causal elements
- Systematic evaluation of causal discovery in visual model based reinforcement learning
- A counterfactual simulation model of causal judgments for physical events
- What would have happened? Counterfactuals, hypotheticals, and causal judgments
- Counterfactuals and the logic of causal selection
- NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
- Github repo: BIG-bench
- Github repo: CausalMBRL
- Github repo: PyWhy
- Github repo: y0 Causal Inference
- Github repo: SayCan
- Reinventing search with a new AI-powered Microsoft Bing and Edge, your copilot for the web
Related Topics
Related Episodes
342