Can Foundation Models Talk Causality?

Moritz Willig, Matej Zečević, Devendra Singh Dhami, Kristian Kersting

Keywords: Foundation models, causality, large-scale language models

TL;DR: Foundation Models have divided AI into 2 camps: those for and against the argument that this will lead us to AGI. We ask the question whether these large scale models handle causal inference that is a core requirement for a system to achieve AGI.

Abstract: Foundation models are subject to an ongoing heated debate, leaving open the question of progress towards AGI and dividing the community into two camps: the ones who see the arguably impressive results as evidence to the scaling hypothesis, and the others who are worried about the lack of interpretability and reasoning capabilities. By investigating to which extent causal representations might be captured by these large scale language models, we make a humble efforts towards resolving the ongoing philosophical conflicts.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2206.10591/code)