getting causal counterfactuals right
CRASS is the first project of apergo.ai. It's aim is to create the decisive step to make causal and counterfactual reasoning of neural networks testable and have clear standards on how to judge counterfactual reasoning in AI in general.
visit: CRASS - GitHub
and see our Paper
accepted at LREC 2022
CRASS got accepted to be part of Google's and OpenAI's BIG-Bench
which in turn is part of the broader effort to develop PaLM. Visit the blog post
and see Google's inclusion of a CRASS