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.
@article{arxiv.2206.10591,
title = {Can Foundation Models Talk Causality?},
author = {Moritz Willig and Matej Zečević and Devendra Singh Dhami and Kristian Kersting},
journal= {arXiv preprint arXiv:2206.10591},
year = {2022}
}
Comments
Main paper: 6 pages, References: 1.5 pages, Supplement: 11.5 pages. Main paper: 4 figures, Supplement: 3 figures, 8 tables