Exciting results from StanfordNLP (with D'Oosterlinck from Gent) on Causal Proxies: using symbolic surrogate models for interpreting deep learning, and testing for causality using counterfactual interventions.
Karel@KarelDoostrlnck
🚨Preprint🚨 Interpretable explanations of NLP models are a prerequisite for numerous goals (e.g. safety, trust). We introduce Causal Proxy Models, which provide rich concept-level explanations and can even entirely replace the models they explain. arxiv.org/abs/2209.14279 1/7
English
